Abstract Volumetric inverse rendering seeks to recover the optical properties of participating media from images. Existing approaches either rely on differentiable stochastic light transport simulation, which require substantial algorithmic effort, or use simplified models that fail to capture global illumination. We propose a formulation that reconciles physically complete light transport with general‐purpose neural optimization. The optical properties of the medium and the full light field are represented as neural fields and estimated through a joint optimization process. Global illumination is enforced via a residual objective derived from the Radiative Transfer Equation in local differential form, complemented by a volume rendering term along primary viewing rays to mitigate low‐frequency bias. We demonstrate reconstruction of spatially varying, color‐resolved scattering, absorption, and phase function parameters from multi‐view images. Beyond reconstruction, the same framework supports learning generative models of participating media with physical optical properties under global illumination.

Real-time path tracing increasingly operates under extremely low sampling budgets, often below one sample per pixel, as rendering complexity, resolution, and frame-rate requirements continue to rise. Superresolution is widely used in production because it reduces path-tracing cost by tracing rays on a coarser image grid and reconstructing missing details. This creates a uniform tradeoff between cost and spatial detail: every image region receives the same reduced ray budget, although path-tracing noise, reconstruction difficulty, and perceptual importance vary strongly across the image. Adaptive sampling offers a compelling alternative, but existing end-to-end approaches rely on approximations that break down in sparse regimes. We introduce an end-to-end adaptive sampling and denoising pipeline explicitly designed for the sub-1-spp regime. Our method uses a stochastic formulation of sample placement that enables gradient estimation despite discrete sampling decisions, allowing stable training of a neural sampler at low sampling budgets. To better align optimization with human perception, we propose a tone-mapping-aware training pipeline that integrates differentiable filmic operators and a state-of-the-art perceptual loss, preventing oversampling of regions with low visual impact. In addition, we introduce a gather-based pyramidal denoising filter and a learnable generalization of albedo demodulation tailored to sparse sampling. Our results show consistent improvements over uniform sparse sampling, with notably better reconstruction of perceptually critical details such as specular highlights and shadow boundaries, and demonstrate that adaptive sampling remains effective in the sub-1-spp regime.

Our ability to perceive and navigate the spatial world is a cornerstone of human experience, relying on the integration of visual and auditory cues to form a coherent sense of depth and distance. In stereoscopic 3D vision, depth perception requires fixation of both eyes on a target object, which is achieved through vergence movements, with convergence for near objects and divergence for distant ones. In contrast, auditory cues provide complementary depth information through variations in loudness, interaural differences (IAD), and the frequency spectrum. We investigate the interaction between visual and auditory cues and examine how contradictory auditory information can overdrive visual depth perception in virtual reality (VR). When a new visual target appears, we introduce a spatial discrepancy between the visual and auditory cues: the visual target is shifted closer to the previously fixated object, while the corresponding sound localization is displaced in the opposite direction. By integrating these conflicting cues through multimodal processing, the resulting percept is biased toward the intended depth location. This audiovisual fusion counteracts depth compression, thus reducing the required vergence magnitude and enabling faster gaze retargeting. Such audio-driven depth enhancement may further help mitigate the vergence-accommodation conflict (VAC) in scenarios where physical depth must be compressed. In a series of psychophysical studies, we first assess the efficiency of depth overdriving for various VR-relevant combinations of initial fixations and shifted target locations, considering different scenarios of audio displacements and their loudness and frequency parameters. Next, we quantify the resulting speedup in gaze retargeting for target shifts that can be successfully overdriven by sound manipulations. Finally, we apply our method in a naturalistic VR scenario where user interface interactions with the scene show an extended perceptual depth.

Accurate prediction of continuous properties is essential to many scientific and engineering tasks. Although deep-learning regressors excel with abundant labels, their accuracy deteriorates in data-scarce regimes. We introduce RankRefine, a model-agnostic, plug-and-play post-hoc refinement technique that injects expert knowledge through pairwise rankings. Given a query item and a small reference set with known properties, RankRefine combines the base regressor’s output with a rank-based estimate via inverse-variance weighting, requiring no retraining. In molecular property prediction task, RankRefine achieves up to 10\% relative reduction in mean absolute error using only 20 pairwise comparisons obtained through a general-purpose large language model (LLM) with no finetuning. As rankings provided by human experts or general-purpose LLMs are sufficient for improving regression across diverse domains, RankRefine offers practicality and broad applicability, especially in low-data settings.

Abstract We demonstrate generating HDR images using the concerted action of multiple black‐box, pre‐trained LDR image diffusion models. Common diffusion models are not HDR as, first, there is no sufficiently large HDR image dataset available to re‐train them, and, second, even if it was, re‐training such models is impossible for most compute budgets. Instead, we seek inspiration from the HDR image capture literature that traditionally fuses sets of LDR images, called “exposure brackets”, to produce a single HDR image. We operate multiple denoising processes to generate multiple LDR brackets that together form a valid HDR result. To this end, we introduce a brackets consistency term into the diffusion process to couple the brackets such that they agree across the exposure range they share. We demonstrate HDR versions of state‐of‐the‐art unconditional and conditional as well as restoration‐type (LDR2HDR) generative modeling.

Abstract Fractal geometry, defined by self‐similar patterns across scales, is crucial for understanding natural structures. This work addresses the fractal inverse problem, which involves extracting fractal codes from images to explain these patterns and synthesize them at arbitrary finer scales. We introduce a novel algorithm that optimizes Iterated Function System parameters using a custom fractal generator combined with differentiable point splatting. By integrating both stochastic and gradient‐based optimization techniques, our approach effectively navigates the complex energy landscapes typical of fractal inversion, ensuring robust performance and the ability to escape local minima. We demonstrate the method's effectiveness through comparisons with various fractal inversion techniques, highlighting its ability to recover high‐quality fractal codes and perform extensive zoom‐ins to reveal intricate patterns from just a single image.

We present MILO (Metric for Image- and Latent-space Optimization), a lightweight, multiscale, perceptual metric for full-reference image quality assessment (FR-IQA). MILO is trained using pseudo-MOS (Mean Opinion Score) supervision, in which reproducible distortions are applied to diverse images and scored via an ensemble of recent quality metrics that account for visual masking effects. This approach enables accurate learning without requiring large-scale human-labeled datasets. Despite its compact architecture, MILO outperforms existing metrics across standard FR-IQA benchmarks and offers fast inference suitable for real-time applications. Beyond quality prediction, we demonstrate the utility of MILO as a perceptual loss in both image and latent domains. In particular, we show that spatial masking modeled by MILO, when applied to latent representations from a VAE encoder within Stable Diffusion, enables efficient and perceptually aligned optimization. By combining spatial masking with a curriculum learning strategy, we first process perceptually less relevant regions before progressively shifting the optimization to more visually distorted areas. This strategy leads to significantly improved performance in tasks like denoising, super-resolution, and face restoration, while also reducing computational overhead. MILO thus functions as both a state-of-the-art image quality metric and as a practical tool for perceptual optimization in generative pipelines.

Markov chain Monte Carlo (MCMC) algorithms are indispensable when sampling from a complex, high-dimensional distribution by a conventional method is intractable. Even though MCMC is a powerful tool, it is also hard to control and tune in practice. Simultaneously achieving both rapid local exploration of the state space and efficient global discovery of the target distribution is a challenging task. In this work, we introduce a novel continuous-time MCMC formulation to the computer science community. Generalizing existing work from the statistics community, we propose a novel framework for adjusting an arbitrary family of Markov processes - used for local exploration of the state space only - to an overall process which is invariant with respect to a target distribution. To demonstrate the potential of our framework, we focus on a simple, but yet insightful, application in light transport simulation. As a by-product, we introduce continuous-time MCMC sampling to the computer graphics community. We show how any existing MCMC-based light transport algorithm can be seamlessly integrated into our framework. We prove empirically and theoretically that the integrated version is superior to the ordinary algorithm. In fact, our approach will convert any existing algorithm into a highly parallelizable variant with shorter running time, smaller error and less variance.

Abstract Full‐reference image quality metrics (FR‐IQMs) aim to measure the visual differences between a pair of reference and distorted images, with the goal of accurately predicting human judgments. However, existing FR‐IQMs, including traditional ones like PSNR and SSIM and even perceptual ones such as HDR‐VDP, LPIPS, and DISTS, still fall short in capturing the complexities and nuances of human perception. In this work, rather than devising a novel IQM model, we seek to improve upon the perceptual quality of existing FR‐IQM methods. We achieve this by considering visual masking, an important characteristic of the human visual system that changes its sensitivity to distortions as a function of local image content. Specifically, for a given FR‐IQM metric, we propose to predict a visual masking model that modulates reference and distorted images in a way that penalizes the visual errors based on their visibility. Since the ground truth visual masks are difficult to obtain, we demonstrate how they can be derived in a self‐supervised manner solely based on mean opinion scores (MOS) collected from an FR‐IQM dataset. Our approach results in enhanced FR‐IQM metrics that are more in line with human prediction both visually and quantitatively.

Abstract Radiance field methods represent the state of the art in reconstructing complex scenes from multi‐view photos. However, these reconstructions often suffer from one or both of the following limitations: First, they typically represent scenes in low dynamic range (LDR), which restricts their use to evenly lit environments and hinders immersive viewing experiences. Secondly, their reliance on a pinhole camera model, assuming all scene elements are in focus in the input images, presents practical challenges and complicates refocusing during novel‐view synthesis. Addressing these limitations, we present a lightweight method based on 3D Gaussian Splatting that utilizes multi‐view LDR images of a scene with varying exposure times, apertures, and focus distances as input to reconstruct a high‐dynamic‐range (HDR) radiance field. By incorporating analytical convolutions of Gaussians based on a thin‐lens camera model as well as a tonemapping module, our reconstructions enable the rendering of HDR content with flexible refocusing capabilities. We demonstrate that our combined treatment of HDR and depth of field facilitates real‐time cinematic rendering, outperforming the state of the art.

Gaussian scale spaces are a cornerstone of signal representation and processing, with applications in filtering, multiscale analysis, anti-aliasing, and many more. However, obtaining such a scale space is costly and cumbersome, in particular for continuous representations such as neural fields. We present an efficient and lightweight method to learn the fully continuous, anisotropic Gaussian scale space of an arbitrary signal. Based on Fourier feature modulation and Lipschitz bounding, our approach is trained self-supervised, i.e., training does not require any manual filtering. Our neural Gaussian scale-space fields faithfully capture multiscale representations across a broad range of modalities, and support a diverse set of applications. These include images, geometry, light-stage data, texture anti-aliasing, and multiscale optimization.

The real world exhibits rich structure and detail across many scales of observation. It is difficult, however, to capture and represent a broad spectrum of scales using ordinary images. We devise a novel paradigm for learning a representation that captures an orders-of-magnitude variety of scales from an unstructured collection of ordinary images. We treat this collection as a distribution of scale-space slices to be learned using adversarial training, and additionally enforce coherency across slices. Our approach relies on a multiscale generator with carefully injected procedural frequency content, which allows to interactively explore the emerging continuous scale space. Training across vastly different scales poses challenges regarding stability, which we tackle using a supervision scheme that involves careful sampling of scales. We show that our generator can be used as a multiscale generative model, and for reconstructions of scale spaces from unstructured patches. Significantly outperforming the state of the art, we demonstrate zoom-in factors of up to 256x at high quality and scale consistency.

Most in-the-wild images are stored in Low Dynamic Range (LDR) form, serving as a partial observation of the High Dynamic Range (HDR) visual world. Despite limited dynamic range, these LDR images are often captured with different exposures, implicitly containing information about the underlying HDR image distribution. Inspired by this intuition, in this work we present, to the best of our knowledge, the first method for learning a generative model of HDR images from in-the-wild LDR image collections in a fully unsupervised manner. The key idea is to train a generative adversarial network (GAN) to generate HDR images which, when projected to LDR under various exposures, are indistinguishable from real LDR images. The projection from HDR to LDR is achieved via a camera model that captures the stochasticity in exposure and camera response function. Experiments show that our method GlowGAN can synthesize photorealistic HDR images in many challenging cases such as landscapes, lightning, or windows, where previous supervised generative models produce overexposed images. With the assistance of GlowGAN, we showcase the novel application of unsupervised inverse tone mapping (GlowGAN-ITM) that sets a new paradigm in this field. Unlike previous methods that gradually complete information from LDR input, GlowGAN-ITM searches the entire HDR image manifold modeled by GlowGAN for the HDR images which can be mapped back to the LDR input. GlowGAN-ITM achieves more realistic reconstruction of overexposed regions compared to state-of-the-art supervised learning models, despite not requiring HDR images or paired multi-exposure images for training.

3D printing based on continuous deposition of materials, such as filament-based 3D printing, has seen widespread adoption thanks to its versatility in working with a wide range of materials. An important shortcoming of this type of technology is its limited multi-material capabilities. While there are simple hardware designs that enable multi-material printing in principle, the required software is heavily underdeveloped. A typical hardware design fuses together individual materials fed into a single chamber from multiple inlets before they are deposited. This design, however, introduces a time delay between the intended material mixture and its actual deposition. In this work, inspired by diverse path planning research in robotics, we show that this mechanical challenge can be addressed via improved printer control. We propose to formulate the search for optimal multi-material printing policies in a reinforcement learning setup. We put forward a simple numerical deposition model that takes into account the non-linear material mixing and delayed material deposition. To validate our system we focus on color fabrication, a problem known for its strict requirements for varying material mixtures at a high spatial frequency. We demonstrate that our learned control policy outperforms state-of-the-art hand-crafted algorithms.

When dealing with difficult inverse problems such as inverse rendering, using Monte Carlo estimated gradients to optimise parameters can slow down convergence due to variance. Averaging many gradient samples in each iteration reduces this variance trivially. However, for problems that require thousands of optimisation iterations, the computational cost of this approach rises quickly.

A faithful reproduction of gloss is inherently difficult because of the limited dynamic range, peak luminance, and 3D capabilities of display devices. This work investigates how the display capabilities affect gloss appearance with respect to a real-world reference object. To this end, we employ an accurate imaging pipeline to achieve a perceptual gloss match between a virtual and real object presented side-by-side on an augmented-reality high-dynamic-range (HDR) stereoscopic display, which has not been previously attained to this extent. Based on this precise gloss reproduction, we conduct a series of gloss matching experiments to study how gloss perception degrades based on individual factors: object albedo, display luminance, dynamic range, stereopsis, and tone mapping. We support the study with a detailed analysis of individual factors, followed by an in-depth discussion on the observed perceptual effects. Our experiments demonstrate that stereoscopic presentation has a limited effect on the gloss matching task on our HDR display. However, both reduced luminance and dynamic range of the display reduce the perceived gloss. This means that the visual system cannot compensate for the changes in gloss appearance across luminance (lack of gloss constancy), and the tone mapping operator should be carefully selected when reproducing gloss on a low dynamic range (LDR) display.

Abstract Video frame interpolation (VFI) enables many important applications such as slow motion playback and frame rate conversion. However, one major challenge in using VFI is accurately handling high dynamic range (HDR) scenes with complex motion. To this end, we explore the possible advantages of dual‐exposure sensors that readily provide sharp short and blurry long exposures that are spatially registered and whose ends are temporally aligned. This way, motion blur registers temporally continuous information on the scene motion that, combined with the sharp reference, enables more precise motion sampling within a single camera shot. We demonstrate that this facilitates a more complex motion reconstruction in the VFI task, as well as HDR frame reconstruction that so far has been considered only for the originally captured frames, not in‐between interpolated frames. We design a neural network trained in these tasks that clearly outperforms existing solutions. We also propose a metric for scene motion complexity that provides important insights into the performance of VFI methods at test time.

Abstract The humble loop shrinking property played a central role in the inception of modern topology but it has been eclipsed by more abstract algebraic formalisms. This is particularly true in the context of detecting relevant non‐contractible loops on surfaces where elaborate homological and/or graph theoretical constructs are favored in algorithmic solutions. In this work, we devise a variational analogy to the loop shrinking property and show that it yields a simple, intuitive, yet powerful solution allowing a streamlined treatment of the problem of handle and tunnel loop detection. Our formalization tracks the evolution of a diffusion front randomly initiated on a single location on the surface. Capitalizing on a diffuse interface representation combined with a set of rules for concurrent front interactions, we develop a dynamic data structure for tracking the evolution on the surface encoded as a sparse matrix which serves for performing both diffusion numerics and loop detection and acts as the workhorse of our fully parallel implementation. The substantiated results suggest our approach outperforms state of the art and robustly copes with highly detailed geometric models. As a byproduct, our approach can be used to construct Reeb graphs by diffusion thus avoiding commonly encountered issues when using Morse functions.

Eye-tracking technology has started to become an integral component of new display devices such as virtual and augmented reality headsets. Applications of gaze information range from new interaction techniques that exploit eye patterns to gaze-contingent digital content creation. However, system latency is still a significant issue in many of these applications because it breaks the synchronization between the current and measured gaze positions. Consequently, it may lead to unwanted visual artifacts and degradation of the user experience. In this work, we focus on foveated rendering applications where the quality of an image is reduced towards the periphery for computational savings. In foveated rendering, the presence of system latency leads to delayed updates to the rendered frame, making the quality degradation visible to the user. To address this issue and to combat system latency, recent work proposes using saccade landing position prediction to extrapolate gaze information from delayed eye tracking samples. Although the benefits of such a strategy have already been demonstrated, the solutions range from simple and efficient ones, which make several assumptions about the saccadic eye movements, to more complex and costly ones, which use machine learning techniques. However, it is unclear to what extent the prediction can benefit from accounting for additional factors and how more complex predictions can be performed efficiently to respect the latency requirements. This paper presents a series of experiments investigating the importance of different factors for saccades prediction in common virtual and augmented reality applications. In particular, we investigate the effects of saccade orientation in 3D space and smooth pursuit eye-motion (SPEM) and how their influence compares to the variability across users. We also present a simple, yet efficient post-hoc correction method that adapts existing saccade prediction methods to handle these factors without performing extensive data collection. Furthermore, our investigation and the correction technique may also help future developments of machine-learning-based techniques by limiting the required amount of training data.

Point patterns are characterized by their density and correlation. While spatial variation of density is well-understood, analysis and synthesis of spatially-varying correlation is an open challenge. No tools are available to intuitively edit such point patterns, primarily due to the lack of a compact representation for spatially varying correlation. We propose a low-dimensional perceptual embedding for point correlations. This embedding can map point patterns to common three-channel raster images, enabling manipulation with off-the-shelf image editing software. To synthesize back point patterns, we propose a novel edge-aware objective that carefully handles sharp variations in density and correlation. The resulting framework allows intuitive and backward-compatible manipulation of point patterns, such as recoloring, relighting to even texture synthesis that have not been available to 2D point pattern design before. Effectiveness of our approach is tested in several user experiments. Code is available at https://github.com/xchhuang/patternshop.

Neural fields are evolving towards a general-purpose continuous representation for visual computing. Yet, despite their numerous appealing properties, they are hardly amenable to signal processing. As a remedy, we present a method to perform general continuous convolutions with general continuous signals such as neural fields. Observing that piecewise polynomial kernels reduce to a sparse set of Dirac deltas after repeated differentiation, we leverage convolution identities and train a repeated integral field to efficiently execute large-scale convolutions. We demonstrate our approach on a variety of data modalities and spatially-varying kernels.

In everyday photography, physical limitations of camera sensors and lenses frequently lead to a variety of degradations in captured images such as saturation or defocus blur. A common approach to overcome these limitations is to resort to image stack fusion, which involves capturing multiple images with different focal distances or exposures. For instance, to obtain an all-in-focus image, a set of multi-focus images is captured. Similarly, capturing multiple exposures allows for the reconstruction of high dynamic range. In this paper, we present a novel approach that combines neural fields with an expressive camera model to achieve a unified reconstruction of an all-in-focus high-dynamic-range image from an image stack. Our approach is composed of a set of specialized implicit neural representations tailored to address specific sub-problems along our pipeline: We use neural implicits to predict flow to overcome misalignments arising from lens breathing, depth, and all-in-focus images to account for depth of field, as well as tonemapping to deal with sensor responses and saturation - all trained using a physically inspired supervision structure with a differentiable thin lens model at its core. An important benefit of our approach is its ability to handle these tasks simultaneously or independently, providing flexible post-editing capabilities such as refocusing and exposure adjustment. By sampling the three primary factors in photography within our framework (focal distance, aperture, and exposure time), we conduct a thorough exploration to gain valuable insights into their significance and impact on overall reconstruction quality. Through extensive validation, we demonstrate that our method outperforms existing approaches in both depth-from-defocus and all-in-focus image reconstruction tasks. Moreover, our approach exhibits promising results in each of these three dimensions, showcasing its potential to enhance captured image quality and provide greater control in post-processing.

Neural networks are powerful surrogates for numerous forward processes.The inversion of such surrogates is extremely valuable in science and engineering. The most important property of a successful neural inverse method is the performance of its solutions when deployed in the real world, i.e., on the native forward process (and not only the learned surrogate). We propose Autoinverse, a highly automated approach for inverting neural network surrogates. Our main insight is to seek inverse solutions in the vicinity of reliable data which have been sampled form the forward process and used for training the surrogate model. Autoinverse finds such solutions by taking into account the predictive uncertainty of the surrogate and minimizing it during the inversion. Apart from high accuracy, Autoinverse enforces the feasibility of solutions, comes with embedded regularization, and is initialization free. We verify our proposed method through addressing a set of real-world problems in control, fabrication, and design.

A good match of material appearance between real-world objects and their digital on-screen representations is critical for many applications such as fabrication, design, and e-commerce. However, faithful appearance reproduction is challenging, especially for complex phenomena, such as gloss. In most cases, the view-dependent nature of gloss and the range of luminance values required for reproducing glossy materials exceeds the current capabilities of display devices. As a result, appearance reproduction poses significant problems even with accurately rendered images. This paper studies the gap between the gloss perceived from real-world objects and their digital counterparts. Based on our psychophysical experiments on a wide range of 3D printed samples and their corresponding photographs, we derive insights on the influence of geometry, illumination, and the display’s brightness and measure the change in gloss appearance due to the display limitations. Our evaluation experiments demonstrate that using the prediction to correct material parameters in a rendering system improves the match of gloss appearance between real objects and their visualization on a display device.

Abstract Point pattern synthesis requires capturing both local and non‐local correlations from a given exemplar. Recent works employ deep hierarchical representations from VGG‐19 [SZ15] convolutional network to capture the features for both point‐pattern and texture synthesis. In this work, we develop a simplified optimization pipeline that uses more traditional Gabor transform‐based features. These features when convolved with simple random filters gives highly expressive feature maps. The resulting framework requires significantly less feature maps compared to VGG‐19‐based methods [TLH19; RGF∗20], better captures both the local and non‐local structures, does not require any specific data set training and can easily extend to handle multi‐class and multi‐attribute point patterns, e.g., disk and other element distributions. To validate our pipeline, we perform qualitative and quantitative analysis on a large variety of point patterns to demonstrate the effectiveness of our approach. Finally, to better understand the impact of random filters, we include a spectral analysis using filters with different frequency bandwidths.

Abstract High Dynamic Range (HDR) content is becoming ubiquitous due to the rapid development of capture technologies. Nevertheless, the dynamic range of common display devices is still limited, therefore tone mapping (TM) remains a key challenge for image visualization. Recent work has demonstrated that neural networks can achieve remarkable performance in this task when compared to traditional methods, however, the quality of the results of these learning‐based methods is limited by the training data. Most existing works use as training set a curated selection of best‐performing results from existing traditional tone mapping operators (often guided by a quality metric), therefore, the quality of newly generated results is fundamentally limited by the performance of such operators. This quality might be even further limited by the pool of HDR content that is used for training. In this work we propose a learning‐based self‐supervised tone mapping operator that is trained at test time specifically for each HDR image and does not need any data labeling. The key novelty of our approach is a carefully designed loss function built upon fundamental knowledge on contrast perception that allows for directly comparing the content in the HDR and tone mapped images. We achieve this goal by reformulating classic VGG feature maps into feature contrast maps that normalize local feature differences by their average magnitude in a local neighborhood, allowing our loss to account for contrast masking effects. We perform extensive ablation studies and exploration of parameters and demonstrate that our solution outperforms existing approaches with a single set of fixed parameters, as confirmed by both objective and subjective metrics.

In computational design and fabrication, neural networks are becoming important surrogates for bulky forward simulations. A long-standing, intertwined question is that of inverse design: how to compute a design that satisfies a desired target performance? Here, we show that the piecewise linear property, very common in everyday neural networks, allows for an inverse design formulation based on mixed-integer linear programming. Our mixed-integer inverse design uncovers globally optimal or near optimal solutions in a principled manner. Furthermore, our method significantly facilitates emerging, but challenging, combinatorial inverse design tasks, such as material selection. For problems where finding the optimal solution is intractable, we develop an efficient yet near-optimal hybrid approach. Eventually, our method is able to find solutions provably robust to possible fabrication perturbations among multiple designs with similar performances. Our code and data are available at https://gitlab.mpi-klsb.mpg.de/nansari/mixed-integer-neural-inverse-design.

High-fidelity reconstruction of dynamic fluids from sparse multiview RGB videos remains a formidable challenge, due to the complexity of the underlying physics as well as the severe occlusion and complex lighting in the captured data. Existing solutions either assume knowledge of obstacles and lighting, or only focus on simple fluid scenes without obstacles or complex lighting, and thus are unsuitable for real-world scenes with unknown lighting conditions or arbitrary obstacles. We present the first method to reconstruct dynamic fluid phenomena by leveraging the governing physics (ie, Navier -Stokes equations) in an end-to-end optimization from a mere set of sparse video frames without taking lighting conditions, geometry information, or boundary conditions as input. Our method provides a continuous spatio-temporal scene representation using neural networks as the ansatz of density and velocity solution functions for fluids as well as the radiance field for static objects. With a hybrid architecture that separates static and dynamic contents apart, fluid interactions with static obstacles are reconstructed for the first time without additional geometry input or human labeling. By augmenting time-varying neural radiance fields with physics-informed deep learning, our method benefits from the supervision of images and physical priors. Our progressively growing model with regularization further disentangles the density-color ambiguity in the radiance field, which allows for a more robust optimization from the given input of sparse views. A pretrained density-to-velocity fluid model is leveraged in addition as the data prior to avoid suboptimal velocity solutions which underestimate vorticity but trivially fulfill physical equations. Our method exhibits high-quality results with relaxed constraints and strong flexibility on a representative set of synthetic and real flow captures. Code and sample tests are at https://people.mpi-inf.mpg.de/~mchu/projects/PI-NeRF/.

Streaming rendered 3D content over a network to a thin client device, such as a phone or a VR/AR headset, brings high-fidelity graphics to platforms where it would not normally possible due to thermal, power, or cost constraints. Streamed 3D content must be transmitted with a representation that is both robust to latency and potential network dropouts. Transmitting a video stream and reprojecting to correct for changing viewpoints fails in the presence of disocclusion events; streaming scene geometry and performing high-quality rendering on the client is not possible on limited-power mobile GPUs. To balance the competing goals of disocclusion robustness and minimal client workload, we introduce QuadStream , a new streaming content representation that reduces motion-to-photon latency by allowing clients to efficiently render novel views without artifacts caused by disocclusion events. Motivated by traditional macroblock approaches to video codec design, we decompose the scene seen from positions in a view cell into a series of quad proxies , or view-aligned quads from multiple views. By operating on a rasterized G-Buffer, our approach is independent of the representation used for the scene itself; the resulting QuadStream is an approximate geometric representation of the scene that can be reconstructed by a thin client to render both the current view and nearby adjacent views. Our technical contributions are an efficient parallel quad generation, merging, and packing strategy for proxy views covering potential client movement in a scene; a packing and encoding strategy that allows masked quads with depth information to be transmitted as a frame-coherent stream; and an efficient rendering approach for rendering our QuadStream representation into entirely novel views on thin clients. We show that our approach achieves superior quality compared both to video data streaming methods, and to geometry-based streaming.

We propose a multi-class point optimization formulation based on continuous Wasserstein barycenters. Our formulation is designed to handle hundreds to thousands of optimization objectives and comes with a practical optimization scheme. We demonstrate the effectiveness of our framework on various sampling applications like stippling, object placement, and Monte-Carlo integration. We a derive multi-class error bound for perceptual rendering error which can be minimized using our optimization. We provide source code at https://github.com/iribis/filtered-sliced-optimal-transport.

The reflectance field of a face describes the reflectance properties responsible for complex lighting effects including diffuse, specular, inter-reflection and self shadowing. Most existing methods for estimating the face reflectance from a monocular image assume faces to be diffuse with very few approaches adding a specular component. This still leaves out important perceptual aspects of reflectance such as higher-order global illumination effects and self-shadowing. We present a new neural representation for face reflectance where we can estimate all components of the reflectance responsible for the final appearance from a monocular image. Instead of modeling each component of the reflectance separately using parametric models, our neural representation allows us to generate a basis set of faces in a geometric deformation-invariant space, parameterized by the input light direction, viewpoint and face geometry. We learn to reconstruct this reflectance field of a face just from a monocular image, which can be used to render the face from any viewpoint in any light condition. Our method is trained on a light-stage dataset, which captures 300 people illuminated with 150 light conditions from 8 viewpoints. We show that our method outperforms existing monocular reflectance reconstruction methods due to better capturing of physical effects, such as sub-surface scattering, specularities, self-shadows and other higher-order effects.

Most 3D face reconstruction methods rely on 3D morphable models, which disentangle the space of facial deformations into identity and expression geometry, and skin reflectance. These models are typically learned from a limited number of 3D scans and thus do not generalize well across different identities and expressions. We present the first approach to learn complete 3D models of face identity and expression geometry, and reflectance, just from images and videos. The virtually endless collection of such data, in combination with our self-supervised learning-based approach allows for learning face models that generalize beyond the span of existing approaches. Our network design and loss functions ensure a disentangled parameterization of not only identity and albedo, but also, for the first time, an expression basis. Our method also allows for in-the-wild monocular reconstruction at test time. We show that our learned models better generalize and lead to higher quality image-based reconstructions than existing approaches. We show that the learned model can also be personalized to a video, for a better capture of the geometry and albedo.

Video-based human motion transfer creates video animations of humans following a source motion. Current methods show remarkable results for tightly-clad subjects. However, the lack of temporally consistent handling of plausible clothing dynamics, including fine and high-frequency details, significantly limits the attainable visual quality. We address these limitations for the first time in the literature and present a new framework which performs high-fidelity and temporally-consistent human motion transfer with natural pose-dependent non-rigid deformations, for several types of loose garments. In contrast to the previous techniques, we perform image generation in three subsequent stages: synthesizing human shape, structure, and appearance. Given a monocular RGB video of an actor, we train a stack of recurrent deep neural networks that generate these intermediate representations from 2D poses and their temporal derivatives. Splitting the difficult motion transfer problem into subtasks that are aware of the temporal motion context helps us to synthesize results with plausible dynamics and pose-dependent detail. It also allows artistic control of results by manipulation of individual framework stages. In the experimental results, we significantly outperform the state-of-the-art in terms of video realism. The source code is available at https://graphics.tu-bs.de/publications/kappel2020high-fidelity.

We present the first deep implicit 3D morphable model (i3DMM) of full heads. Unlike earlier morphable face models it not only captures identity-specific geometry, texture, and expressions of the frontal face, but also models the entire head, including hair. We collect a new dataset consisting of 64 people with different expressions and hairstyles to train i3DMM. Our approach has the following favorable properties: (i) It is the first full head morphable model that includes hair. (ii) In contrast to mesh-based models it can be trained on merely rigidly aligned scans, without requiring difficult non-rigid registration. (iii) We design a novel architecture to decouple the shape model into an implicit reference shape and a deformation of this reference shape. With that, dense correspondences between shapes can be learned implicitly. (iv) This architecture allows us to semantically disentangle the geometry and color components, as color is learned in the reference space. Geometry is further disentangled as identity, expressions, and hairstyle, while color is disentangled as identity and hairstyle components. We show the merits of i3DMM using ablation studies, comparisons to state-of-the-art models, and applications such as semantic head editing and texture transfer. We will make our model publicly available1.

3D hand pose estimation from monocular videos is a long-standing and challenging problem, which is now seeing a strong upturn. In this work, we address it for the first time using a single event camera, i.e., an asynchronous vision sensor reacting on brightness changes. Our EventHands approach has characteristics previously not demonstrated with a single RGB or depth camera such as high temporal resolution at low data throughputs and real-time performance at 1000 Hz. Due to the different data modality of event cameras compared to classical cameras, existing methods cannot be directly applied to and re-trained for event streams. We thus design a new neural approach which accepts a new event stream representation suitable for learning, which is trained on newly-generated synthetic event streams and can generalise to real data. Experiments show that EventHands outperforms recent monocular methods using a colour (or depth) camera in terms of accuracy and its ability to capture hand motions of unprecedented speed. Our method, the event stream simulator and the dataset are publicly available (see https://4dqv.mpi-inf.mpg.de/EventHands/).

There are concerns that new approaches to the synthesis of high quality face videos may be misused to manipulate videos with malicious intent. The research community therefore developed methods for the detection of modified footage and assembled benchmark datasets for this task. In this paper, we examine how the performance of forgery detectors depends on the presence of artefacts that the human eye can see. We introduce a new benchmark dataset for face video forgery detection, of unprecedented quality. It allows us to demonstrate that existing detection techniques have difficulties detecting fakes that reliably fool the human eye. We thus introduce a new family of detectors that examine combinations of spatial and temporal features and outperform existing approaches both in terms of detection accuracy and generalization.

We propose the first approach to synthesize the synchronous 3D conversational body and hand gestures, as well as 3D face and head animations, of a virtual character from speech input. Our algorithm uses a CNN architecture that leverages the inherent correlation between facial expression and hand gestures. Synthesis of conversational body gestures is a multi-modal problem since many similar gestures can plausibly accompany the same input speech. To synthesize plausible body gestures in this setting, we train a Generative Adversarial Network (GAN) based model that measures the plausibility of the generated sequences of 3D body motion when paired with the input audio features. We also contribute a new corpus that contains more than 33 hours of annotated data from in-the-wild videos of talking people. To this end, we apply state-of-the-art monocular approaches for 3D body and hand pose estimation as well as 3D face performance capture to the video corpus. In this way, we can train on orders of magnitude more data than previous algorithms that resort to complex in-studio motion capture solutions, and thereby train more expressive synthesis algorithms. Our experiments and user study show the state-of-the-art quality of our speech-synthesized full 3D character animations.

Learning neural radiance fields of a scene has recently allowed realistic novel view synthesis of the scene, but they are limited to synthesize images under the original fixed lighting condition. Therefore, they are not flexible for the eagerly desired tasks like relighting, scene editing and scene composition. To tackle this problem, several recent methods propose to disentangle reflectance and illumination from the radiance field. These methods can cope with solid objects with opaque surfaces but participating media are neglected. Also, they take into account only direct illumination or at most one-bounce indirect illumination, thus suffer from energy loss due to ignoring the high-order indirect illumination. We propose to learn neural representations for participating media with a complete simulation of global illumination. We estimate direct illumination via ray tracing and compute indirect illumination with spherical harmonics. Our approach avoids computing the lengthy indirect bounces and does not suffer from energy loss. Our experiments on multiple scenes show that our approach achieves superior visual quality and numerical performance compared to state-of-the-art methods, and it can generalize to deal with solid objects with opaque surfaces as well.

Abstract Streaming rendering, e.g., rendering in the cloud and streaming via a mobile connection, suffers from increased latency and unreliable connections. High quality framerate upsampling can hide these issues, especially when capturing shading into an atlas and transmitting it alongside geometric information. The captured shading information must consider triangle footprints and temporal stability to ensure efficient video encoding. Previous approaches only consider either temporal stability or sample distributions, but none focuses on both. With SnakeBinning, we present an efficient triangle packing approach that adjusts sample distributions and caters for temporal coherence. Using a multi‐dimensional binning approach, we enforce tight packing among triangles while creating optimal sample distributions. Our binning is built on top of hardware supported real‐time rendering where bins are mapped to individual pixels in a virtual framebuffer. Fragment shader interlock and atomic operations enforce global ordering of triangles within each bin, and thus temporal coherence according to the primitive order is achieved. Resampling the bin distribution guarantees high occupancy among all bins and a dense atlas packing. Shading samples are directly captured into the atlas using a rasterization pass, adjusting samples for perspective effects and creating a tight packing. Comparison to previous atlas packing approaches shows that our approach is faster than previous work and achieves the best sample distributions while maintaining temporal coherence. In this way, SnakeBinning achieves the highest rendering quality under equal atlas memory requirements. At the same time, its temporal coherence ensures that we require equal or less bandwidth than previous state‐of‐the‐art. As SnakeBinning outperforms previous approach in all relevant aspects, it is the preferred choice for texture‐based streaming rendering.

Photorealistic editing of head portraits is a challenging task as humans are very sensitive to inconsistencies in faces. We present an approach for high-quality intuitive editing of the camera viewpoint and scene illumination (parameterised with an environment map) in a portrait image. This requires our method to capture and control the full reflectance field of the person in the image. Most editing approaches rely on supervised learning using training data captured with setups such as light and camera stages. Such datasets are expensive to acquire, not readily available and do not capture all the rich variations of in-the-wild portrait images. In addition, most supervised approaches only focus on relighting, and do not allow camera viewpoint editing. Thus, they only capture and control a subset of the reflectance field. Recently, portrait editing has been demonstrated by operating in the generative model space of StyleGAN. While such approaches do not require direct supervision, there is a significant loss of quality when compared to the supervised approaches. In this paper, we present a method which learns from limited supervised training data. The training images only include people in a fixed neutral expression with eyes closed, without much hair or background variations. Each person is captured under 150 one-light-at-a-time conditions and under 8 camera poses. Instead of training directly in the image space, we design a supervised problem which learns transformations in the latent space of StyleGAN. This combines the best of supervised learning and generative adversarial modeling. We show that the StyleGAN prior allows for generalisation to different expressions, hairstyles and backgrounds. This produces high-quality photorealistic results for in-the-wild images and significantly outperforms existing methods. Our approach can edit the illumination and pose simultaneously, and runs at interactive rates.

While modern fluid simulation methods achieve high-quality simulation results, it is still a big challenge to interpret and control motion from visual quantities, such as the advected marker density. These visual quantities play an important role in user interactions: Being familiar and meaningful to humans, these quantities have a strong correlation with the underlying motion. We propose a novel data-driven conditional adversarial model that solves the challenging and theoretically ill-posed problem of deriving plausible velocity fields from a single frame of a density field. Besides density modifications, our generative model is the first to enable the control of the results using all of the following control modalities: obstacles, physical parameters, kinetic energy, and vorticity. Our method is based on a new conditional generative adversarial neural network that explicitly embeds physical quantities into the learned latent space, and a new cyclic adversarial network design for control disentanglement. We show the high quality and versatile controllability of our results for density-based inference, realistic obstacle interaction, and sensitive responses to modifications of physical parameters, kinetic energy, and vorticity. Code, models, and results can be found at https://github.com/RachelCmy/den2vel.

Material appearance hinges on material reflectance properties but also surface geometry and illumination. The unlimited number of potential combinations between these factors makes understanding and predicting material appearance a very challenging task. In this work, we collect a large-scale dataset of perceptual ratings of appearance attributes with more than 215,680 responses for 42,120 distinct combinations of material, shape, and illumination. The goal of this dataset is twofold. First, we analyze for the first time the effects of illumination and geometry in material perception across such a large collection of varied appearances. We connect our findings to those of the literature, discussing how previous knowledge generalizes across very diverse materials, shapes, and illuminations. Second, we use the collected dataset to train a deep learning architecture for predicting perceptual attributes that correlate with human judgments. We demonstrate the consistent and robust behavior of our predictor in various challenging scenarios, which, for the first time, enables estimating perceived material attributes from general 2D images. Since our predictor relies on the final appearance in an image, it can compare appearance properties across different geometries and illumination conditions. Finally, we demonstrate several applications that use our predictor, including appearance reproduction using 3D printing, BRDF editing by integrating our predictor in a differentiable renderer, illumination design, or material recommendations for scene design.

Abstract The understanding of material appearance perception is a complex problem due to interactions between material reflectance, surface geometry, and illumination. Recently, Serrano et al. collected the largest dataset to date with subjective ratings of material appearance attributes, including glossiness, metallicness, sharpness and contrast of reflections. In this work, we make use of their dataset to investigate for the first time the impact of the interactions between illumination, geometry, and eight different material categories in perceived appearance attributes. After an initial analysis, we select for further analysis the four material categories that cover the largest range for all perceptual attributes: fabric, plastic, ceramic, and metal. Using a cumulative link mixed model (CLMM) for robust regression, we discover interactions between these material categories and four representative illuminations and object geometries. We believe that our findings contribute to expanding the knowledge on material appearance perception and can be useful for many applications, such as scene design, where any particular material in a given shape can be aligned with dominant classes of illumination, so that a desired strength of appearance attributes can be achieved.

StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination. Three-dimensional morphable face models (3DMMs) on the other hand offer control over the semantic parameters, but lack photorealism when rendered and only model the face interior, not other parts of a portrait image (hair, mouth interior, background). We present the first method to provide a face rig-like control over a pretrained and fixed StyleGAN via a 3DMM. A new rigging network, is trained between the 3DMM's semantic parameters and StyleGAN's input. The network is trained in a self-supervised manner, without the need for manual annotations. At test time, our method generates portrait images with the photorealism of StyleGAN and provides explicit control over the 3D semantic parameters of the face.

Abstract Subdivision surfaces have become an invaluable asset in production environments. While progress over the last years has allowed the use of graphics hardware to meet performance demands during animation and rendering, high‐performance is limited to immutable mesh connectivity scenarios. Motivated by recent progress in mesh data structures, we show how the complete Catmull‐Clark subdivision scheme can be abstracted in the language of linear algebra. While this high‐level formulation allows for a fully parallel implementation with significant performance gains, the underlying algebraic operations require further specialization for modern parallel hardware. Integrating domain knowledge about the mesh matrix data structure, we replace costly general linear algebra operations like matrix‐matrix multiplication by specialized kernels. By further considering innate properties of Catmull‐Clark subdivision, like the quad‐only structure after refinement, we achieve an additional order of magnitude in performance and significantly reduce memory footprints. Our approach can be adapted seamlessly for different use cases, such as regular subdivision of dynamic meshes, fast evaluation for immutable topology and feature‐adaptive subdivision for efficient rendering of animated models. In this way, patchwork solutions are avoided in favor of a streamlined solution with consistent performance gains throughout the production pipeline. The versatility of the sparse matrix linear algebra abstraction underlying our work is further demonstrated by extension to other schemes such as and Loop subdivision.

Abstract The rich and evocative patterns of natural tessellations endow them with an unmistakable artistic appeal and structural properties which are echoed across design, production, and manufacturing. Unfortunately, interactive control of such patterns‐as modeled by Voronoi diagrams, is limited to the simple two dimensional case and does not extend well tofreeform surfaces. We present an approach for direct modeling and editing of such cellular structures on surface meshes. The overall modeling experience is driven by a set of editing primitives which are efficiently implemented on graphics hardware. We feature a novel application for 3D printing on modern support‐free additive manufacturing platforms. Our method decomposes the input surface into a cellular skeletal structure which hosts a set of overlay shells. In this way, material saving can be channeled to the shells while structural stability is channeled to the skeleton. To accommodate the available printer build volume, the cellular structure can be further split into moderately sized parts. Together with shells, they can be conveniently packed to save on production time. The assembly of the printed parts is streamlined by a part numbering scheme which respects the geometric layout of the input model.

Modern 3D printers are capable of printing large-size light-field displays at high-resolutions. However, optimizing such displays in full 3D volume for a given light-field imagery is still a challenging task. Existing light field displays optimize over relatively small resolutions using a few co-planar layers in a 2.5D fashion to keep the problem tractable. In this paper, we propose a novel end-to-end optimization approach that encodes input light field imagery as a continuous-space implicit representation in a neural network. This allows fabricating high-resolution, attenuation-based volumetric displays that exhibit the target light fields. In addition, we incorporate the physical constraints of the material to the optimization such that the result can be printed in practice. Our simulation experiments demonstrate that our approach brings significant visual quality improvement compared to the multilayer and uniform grid-based approaches. We validate our simulations with fabricated prototypes and demonstrate that our pipeline is flexible enough to allow fabrications of both planar and non-planar displays.

We introduce a novel ink selection method for spectral printing. The ink selection algorithm takes a spectral image and a set of inks as input, and selects a subset of those inks that results in optimal spectral reproduction. We put forward an optimization formulation that searches a huge combinatorial space based on mixed integer programming. We show that solving this optimization in the conventional reflectance space is intractable. The main insight of this work is to solve our problem in the spectral absorbance space with a linearized formulation. The proposed ink selection copes with large-size problems for which previous methods are hopeless. We demonstrate the effectiveness of our method in a concrete setting by lifelike reproduction of handmade paintings. For a successful spectral reproduction of high-resolution paintings, we explore their spectral absorbance estimation, efficient coreset representation, and accurate data-driven reproduction.

We suggest to represent an X-Field ---a set of 2D images taken across different view, time or illumination conditions, i.e., video, lightfield, reflectance fields or combinations thereof---by learning a neural network (NN) to map their view, time or light coordinates to 2D images. Executing this NN at new coordinates results in joint view, time or light interpolation. The key idea to make this workable is a NN that already knows the "basic tricks" of graphics (lighting, 3D projection, occlusion) in a hard-coded and differentiable form. The NN represents the input to that rendering as an implicit map, that for any view, time, or light coordinate and for any pixel can quantify how it will move if view, time or light coordinates change (Jacobian of pixel position with respect to view, time, illumination, etc.). Our X-Field representation is trained for one scene within minutes, leading to a compact set of trainable parameters and hence real-time navigation in view, time and illumination.

Laser irradiation induces colors on some industrially important materials, such as stainless steel and titanium. It is however challenging to find marking configurations that create colorful, high-resolution images. The brute-force solution to the gamut exploration problem does not scale with the high-dimensional design space of laser marking. Moreover, there exists no color reproduction workflow capable of reproducing color images with laser marking. Here, we propose a measurement-based, data-driven performance space exploration of the color laser marking process. We formulate this exploration as a search for the Pareto optimal solutions to a multi-objective optimization and solve it using an evolutionary algorithm. The explored set of diverse colors is then utilized to mark high-quality, full-color images.

We introduce a method for egocentric videoconferencing that enables hands-free video calls, for instance by people wearing smart glasses or other mixed-reality devices. Videoconferencing portrays valuable non-verbal communication and face expression cues, but usually requires a front-facing camera. Using a frontal camera in a hands-free setting when a person is on the move is impractical. Even holding a mobile phone camera in the front of the face while sitting for a long duration is not convenient. To overcome these issues, we propose a low-cost wearable egocentric camera setup that can be integrated into smart glasses. Our goal is to mimic a classical video call, and therefore, we transform the egocentric perspective of this camera into a front facing video. To this end, we employ a conditional generative adversarial neural network that learns a transition from the highly distorted egocentric views to frontal views common in videoconferencing. Our approach learns to transfer expression details directly from the egocentric view without using a complex intermediate parametric expressions model, as it is used by related face reenactment methods. We successfully handle subtle expressions, not easily captured by parametric blendshape-based solutions, e.g., tongue movement, eye movements, eye blinking, strong expressions and depth varying movements. To get control over the rigid head movements in the target view, we condition the generator on synthetic renderings of a moving neutral face. This allows us to synthesis results at different head poses. Our technique produces temporally smooth video-realistic renderings in real-time using a video-to-video translation network in conjunction with a temporal discriminator. We demonstrate the improved capabilities of our technique by comparing against related state-of-the art approaches.

We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals. We contribute a new architecture for this CNN, called SelecSLS Net , that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy. In the second stage, a fullyconnected neural network turns the possibly partial (on account of occlusion) 2D pose and 3D pose features for each subject into a complete 3D pose estimate per individual. The third stage applies space-time skeletal model fitting to the predicted 2D and 3D pose per subject to further reconcile the 2D and 3D pose, and enforce temporal coherence. Our method returns the full skeletal pose in joint angles for each subject. This is a further key distinction from previous work that do not produce joint angle results of a coherent skeleton in real time for multi-person scenes. The proposed system runs on consumer hardware at a previously unseen speed of more than 30 fps given 512x320 images as input while achieving state-of-the-art accuracy, which we will demonstrate on a range of challenging real-world scenes.

Editing of portrait images is a very popular and important research topic with a large variety of applications. For ease of use, control should be provided via a semantically meaningful parameterization that is akin to computer animation controls. The vast majority of existing techniques do not provide such intuitive and fine-grained control, or only enable coarse editing of a single isolated control parameter. Very recently, high-quality semantically controlled editing has been demonstrated, however only on synthetically created StyleGAN images. We present the first approach for embedding real portrait images in the latent space of StyleGAN, which allows for intuitive editing of the head pose, facial expression, and scene illumination in the image. Semantic editing in parameter space is achieved based on StyleRig, a pretrained neural network that maps the control space of a 3D morphable face model to the latent space of the GAN. We design a novel hierarchical non-linear optimization problem to obtain the embedding. An identity preservation energy term allows spatially coherent edits while maintaining facial integrity. Our approach runs at interactive frame rates and thus allows the user to explore the space of possible edits. We evaluate our approach on a wide set of portrait photos, compare it to the current state of the art, and validate the effectiveness of its components in an ablation study.

Monocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on data-driven priors that are built from limited 3D face scans. In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces. Our face model is learned using only corpora of in-the-wild video clips collected from the Internet. This virtually endless source of training data enables learning of a highly general 3D face model. In order to achieve this, we propose a novel multi-frame consistency loss that ensures consistent shape and appearance across multiple frames of a subject's face, thus minimizing depth ambiguity. At test time we can use an arbitrary number of frames, so that we can perform both monocular as well as multi-frame reconstruction.

In the ongoing efforts targeting the vectorization of linear algebra primitives, sparse matrix-matrix multiplication (SpGEMM) has received considerably less attention than sparse Matrix-Vector multiplication (SpMV). While both are equally important, this disparity can be attributed mainly to the additional formidable challenges raised by SpGEMM.

Abstract Image metrics predict the perceived per‐pixel difference between a reference image and its degraded (e. g., re‐rendered) version. In several important applications, the reference image is not available and image metrics cannot be applied. We devise a neural network architecture and training procedure that allows predicting the MSE, SSIM or VGG16 image difference from the distorted image alone while the reference is not observed. This is enabled by two insights: The first is to inject sufficiently many un‐distorted natural image patches, which can be found in arbitrary amounts and are known to have no perceivable difference to themselves. This avoids false positives. The second is to balance the learning, where it is carefully made sure that all image errors are equally likely, avoiding false negatives. Surprisingly, we observe that the resulting no‐reference metric, subjectively, can even perform better than the reference‐based one, as it had to become robust against mis‐alignments. We evaluate the effectiveness of our approach in an image‐based rendering context, both quantitatively and qualitatively. Finally, we demonstrate two applications which reduce light field capture time and provide guidance for interactive depth adjustment.

Abstract In this paper, we introduce the CPatch, a curved primitive that can be used to construct arbitrary vector graphics. A CPatch is a generalization of a 2D polygon: Any number of curves up to a cubic degree bound a primitive. We show that a CPatch can be rasterized efficiently in a hierarchical manner on the GPU, locally discarding irrelevant portions of the curves. Our rasterizer is fast and scalable, works on all patches in parallel, and does not require any approximations. We show a parallel implementation of our rasterizer, which naturally supports all kinds of color spaces, blending and super‐sampling. Additionally, we show how vector graphics input can efficiently be converted to a CPatch representation, solving challenges like patch self intersections and false inside‐outside classification. Results indicate that our approach is faster than the state‐of‐the‐art, more flexible and could potentially be implemented in hardware.

Abstract Presenting high‐fidelity 3D content on compact portable devices with low computational power is challenging. Smartphones, tablets and head‐mounted displays (HMDs) suffer from thermal and battery‐life constraints and thus cannot match the render quality of desktop PCs and laptops. Streaming rendering enables to show high‐quality content but can suffer from potentially high latency. We propose an approach to efficiently capture shading samples in object space and packing them into a texture. Streaming this texture to the client, we support temporal frame up‐sampling with high fidelity, low latency and high mobility. We introduce two novel sample distribution strategies and a novel triangle representation in the shading atlas space. Since such a system requires dynamic parallelism, we propose an implementation exploiting the power of hardware‐accelerated tessellation stages. Our approach allows fast de‐coding and rendering of extrapolated views on a client device by using hardware‐accelerated interpolation between shading samples and a set of potentially visible geometry. A comparison to existing shading methods shows that our sample distributions allow better client shading quality than previous atlas streaming approaches and outperforms image‐based methods in all relevant aspects.

Potential visibility has historically always been of importance when rendering performance was insufficient. With the rise of virtual reality, rendering power may once again be insufficient, e.g., for integrated graphics of head-mounted displays. To tackle the issue of efficient potential visibility computations on modern graphics hardware, we introduce the camera offset space (COS). Opposite to how traditional visibility computations work---where one determines which pixels are covered by an object under all potential viewpoints---the COS describes under which camera movement a sample location is covered by a triangle. In this way, the COS opens up a new set of possibilities for visibility computations. By evaluating the pairwise relations of triangles in the COS, we show how to efficiently determine occluded triangles. Constructing the COS for all pixels of a rendered view leads to a complete potentially visible set (PVS) for complex scenes. By fusing triangles to larger occluders, including locations between pixel centers, and considering camera rotations, we describe an exact PVS algorithm that includes all viewing directions inside a view cell. Implementing the COS is a combination of real-time rendering and compute steps. We provide the first GPU PVS implementation that works without preprocessing, on-the-fly, on unconnected triangles. This opens the door to a new approach of rendering for virtual reality head-mounted displays and server-client settings for streaming 3D applications such as video games.

Dubbing is a technique for translating video content from one language to another. However, state-of-the-art visual dubbing techniques directly copy facial expressions from source to target actors without considering identity-specific idiosyncrasies such as a unique type of smile. We present a style-preserving visual dubbing approach from single video inputs, which maintains the signature style of target actors when modifying facial expressions, including mouth motions, to match foreign languages. At the heart of our approach is the concept of motion style, in particular for facial expressions, i.e., the person-specific expression change that is yet another essential factor beyond visual accuracy in face editing applications. Our method is based on a recurrent generative adversarial network that captures the spatiotemporal co-activation of facial expressions, and enables generating and modifying the facial expressions of the target actor while preserving their style. We train our model with unsynchronized source and target videos in an unsupervised manner using cycle-consistency and mouth expression losses, and synthesize photorealistic video frames using a layered neural face renderer. Our approach generates temporally coherent results, and handles dynamic backgrounds. Our results show that our dubbing approach maintains the idiosyncratic style of the target actor better than previous approaches, even for widely differing source and target actors.

Designing point patterns with desired properties can require substantial effort, both in hand-crafting coding and mathematical derivation. Retaining these properties in multiple dimensions or for a substantial number of points can be challenging and computationally expensive. Tackling those two issues, we suggest to automatically generate scalable point patterns from design goals using deep learning. We phrase pattern generation as a deep composition of weighted distance-based unstructured filters. Deep point pattern design means to optimize over the space of all such compositions according to a user-provided point correlation loss , a small program which measures a pattern's fidelity in respect to its spatial or spectral statistics, linear or non-linear (e. g., radial) projections, or any arbitrary combination thereof. Our analysis shows that we can emulate a large set of existing patterns (blue, green, step, projective, stair, etc.-noise), generalize them to countless new combinations in a systematic way and leverage existing error estimation formulations to generate novel point patterns for a user-provided class of integrand functions. Our point patterns scale favorably to multiple dimensions and numbers of points: we demonstrate nearly 10k points in 10-D produced in one second on one GPU. All the resources (source code and the pre-trained networks) can be found at https://sampling.mpi-inf.mpg.de/deepsampling.html.

Current rendering techniques struggle to fulfill quality and power efficiency requirements imposed by new display devices such as virtual reality headsets. A promising solution to overcome these problems is foveated rendering, which exploits gaze information to reduce rendering quality for the peripheral vision where the requirements of the human visual system are significantly lower. Most of the current solutions model the sensitivity as a function of eccentricity, neglecting the fact that it also is strongly influenced by the displayed content. In this work, we propose a new luminance-contrast-aware foveated rendering technique which demonstrates that the computational savings of foveated rendering can be significantly improved if local luminance contrast of the image is analyzed. To this end, we first study the resolution requirements at different eccentricities as a function of luminance patterns. We later use this information to derive a low-cost predictor of the foveated rendering parameters. Its main feature is the ability to predict the parameters using only a low-resolution version of the current frame, even though the prediction holds for high-resolution rendering. This property is essential for the estimation of required quality before the full-resolution image is rendered. We demonstrate that our predictor can efficiently drive the foveated rendering technique and analyze its benefits in a series of user experiments.

We propose the first real-time system for the egocentric estimation of 3D human body pose in a wide range of unconstrained everyday activities. This setting has a unique set of challenges, such as mobility of the hardware setup, and robustness to long capture sessions with fast recovery from tracking failures. We tackle these challenges based on a novel lightweight setup that converts a standard baseball cap to a device for high-quality pose estimation based on a single cap-mounted fisheye camera. From the captured egocentric live stream, our CNN based 3D pose estimation approach runs at 60 Hz on a consumer-level GPU. In addition to the lightweight hardware setup, our other main contributions are: 1) a large ground truth training corpus of top-down fisheye images and 2) a disentangled 3D pose estimation approach that takes the unique properties of the egocentric viewpoint into account. As shown by our evaluation, we achieve lower 3D joint error as well as better 2D overlay than the existing baselines.

Multi-focal plane and multi-layered light-field displays are promising solutions for addressing all visual cues observed in the real world. Unfortunately, these devices usually require expensive optimizations to compute a suitable decomposition of the input light field or focal stack to drive individual display layers. Although these methods provide near-correct image reconstruction, a significant computational cost prevents real-time applications. A simple alternative is a linear blending strategy which decomposes a single 2D image using depth information. This method provides real-time performance, but it generates inaccurate results at occlusion boundaries and on glossy surfaces. This paper proposes a perception-based hybrid decomposition technique which combines the advantages of the above strategies and achieves both real-time performance and high-fidelity results. The fundamental idea is to apply expensive optimizations only in regions where it is perceptually superior, e.g., depth discontinuities at the fovea, and fall back to less costly linear blending otherwise. We present a complete, perception-informed analysis and model that locally determine which of the two strategies should be applied. The prediction is later utilized by our new synthesis method which performs the image decomposition. The results are analyzed and validated in user experiments on a custom multi-plane display.

We present the first end-to-end approach for real-time material estimation for general object shapes with uniform material that only requires a single color image as input. In addition to Lambertian surface properties, our approach fully automatically computes the specular albedo, material shininess, and a foreground segmentation. We tackle this challenging and ill-posed inverse rendering problem using recent advances in image-to-image translation techniques based on deep convolutional encoder-decoder architectures. The underlying core representations of our approach are specular shading, diffuse shading and mirror images, which allow to learn the effective and accurate separation of diffuse and specular albedo. In addition, we propose a novel highly efficient perceptual rendering loss that mimics real-world image formation and obtains intermediate results even during run time. The estimation of material parameters at real-time frame rates enables exciting mixed-reality applications, such as seamless illumination-consistent integration of virtual objects into real-world scenes, and virtual material cloning. We demonstrate our approach in a live setup, compare it to the state of the art, and demonstrate its effectiveness through quantitative and qualitative evaluation.

Abstract We present an efficient modified Newton iteration for the optimization of nonlinear energies on triangle meshes. Noting that the linear mapping between any pair of triangles is a special case of harmonic mapping, we build upon the results of Chen and Weber [ CW17 ]. Based on the complex view of the linear mapping, we show that the Hessian of the isometric energies has a simple and compact analytic expression. This allows us to analytically project the per‐element Hessians to positive semidefinite matrices for efficient Newton iteration. We show that our method outperforms state‐of‐the‐art methods on 2D deformation and parameterization. Further, we inspect the spectra of the per triangle energy Hessians and show that given an initial mapping, simple global scaling can shift the energy towards a more convex state. This allows Newton iteration to converge faster than starting from the given initial state. Additionally, our formulations support adding an energy smoothness term to the optimization with little additional effort, which improves the mapping results such that concentrated distortions are reduced.

Simulating combinations of depth-of-field and motion blur is an important factor to cinematic quality in synthetic images but can take long to compute. Splatting the point-spread function (PSF) of every pixel is general and provides high quality, but requires prohibitive compute time. We accelerate this in two steps: In a pre-process we optimize for sparse representations of the Laplacian of all possible PSFs that we call spreadlets. At runtime, spreadlets can be splat efficiently to the Laplacian of an image. Integrating this image produces the final result. Our approach scales faithfully to strong motion and large out-of-focus areas and compares favorably in speed and quality with off-line and interactive approaches. It is applicable to both synthesizing from pinhole as well as reconstructing from stochastic images, with or without layering.

A large number of imaging and computer graphics applications require localized information on the visibility of image distortions. Existing image quality metrics are not suitable for this task as they provide a single quality value per image. Existing visibility metrics produce visual difference maps, and are specifically designed for detecting just noticeable distortions but their predictions are often inaccurate. In this work, we argue that the key reason for this problem is the lack of large image collections with a good coverage of possible distortions that occur in different applications. To address the problem, we collect an extensive dataset of reference and distorted image pairs together with user markings indicating whether distortions are visible or not. We propose a statistical model that is designed for the meaningful interpretation of such data, which is affected by visual search and imprecision of manual marking. We use our dataset for training existing metrics and we demonstrate that their performance significantly improves. We show that our dataset with the proposed statistical model can be used to train a new CNN-based metric, which outperforms the existing solutions. We demonstrate the utility of such a metric in visually lossless JPEG compression, super-resolution and watermarking.

We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid surface deformations in general scenes. Human performance capture is a challenging problem due to the large range of articulation, potentially fast motion, and considerable non-rigid deformations, even from multi-view data. Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem. We tackle these challenges by a novel approach that employs sparse 2D and 3D human pose detections from a convolutional neural network using a batch-based pose estimation strategy. Joint recovery of per-batch motion allows us to resolve the ambiguities of the monocular reconstruction problem based on a low-dimensional trajectory subspace. In addition, we propose refinement of the surface geometry based on fully automatically extracted silhouettes to enable medium-scale non-rigid alignment. We demonstrate state-of-the-art performance capture results that enable exciting applications such as video editing and free viewpoint video, previously infeasible from monocular video. Our qualitative and quantitative evaluation demonstrates that our approach significantly outperforms previous monocular methods in terms of accuracy, robustness, and scene complexity that can be handled.

We propose a system to infer binocular disparity from a monocular video stream in real-time. Different from classic reconstruction of physical depth in computer vision, we compute perceptually plausible disparity, that is numerically inaccurate, but results in a very similar overall depth impression with plausible overall layout, sharp edges, fine details and agreement between luminance and disparity. We use several simple monocular cues to estimate disparity maps and confidence maps of low spatial and temporal resolution in real-time. These are complemented by spatially-varying, appearance-dependent and class-specific disparity prior maps, learned from example stereo images. Scene classification selects this prior at runtime. Fusion of prior and cues is done by means of robust MAP inference on a dense spatio-temporal conditional random field with high spatial and temporal resolution. Using normal distributions allows this in constant-time, parallel per-pixel work. We compare our approach to previous 2D-to-3D conversion systems in terms of different metrics, as well as a user study and validate our notion of perceptually plausible disparity.

Light fields become a popular representation of three-dimensional scenes, and there is interest in their processing, resampling, and compression. As those operations often result in loss of quality, there is a need to quantify it. In this work, we collect a new dataset of dense reference and distorted light fields as well as the corresponding quality scores which are scaled in perceptual units. The scores were acquired in a subjective experiment using an interactive light-field viewing setup. The dataset contains typical artifacts that occur in light-field processing chain due to light-field reconstruction, multi-view compression, and limitations of automultiscopic displays. We test a number of existing objective quality metrics to determine how well they can predict the quality of light fields. We find that the existing image quality metrics provide good measures of light-field quality, but require dense reference light-fields for optimal performance. For more complex tasks of comparing two distorted light fields, their performance drops significantly, which reveals the need for new, light-field-specific metrics.

We introduce a hierarchical sparse matrix representation (HiSparse) tailored for the graphics processing unit (GPU). The representation adapts to the local nonzero pattern at all levels of the hierarchy and uses reduced bit length for addressing the entries. This allows a smaller memory footprint than standard formats. Executing algorithms on a hierarchical structure on the GPU usually entails significant synchronization and management overhead or slowdowns due to diverging execution paths and memory access patterns. We address these issues by means of a dynamic scheduling strategy specifically designed for executing algorithms on top of a hierarchical matrix on the GPU. The evaluation of our implementation of basic linear algebra routines, suggests that our hierarchical format is competitive to highly optimized standard libraries and significantly outperforms them in the case of transpose matrix operations. The results point towards the viability of hierarchical matrix formats on massively parallel devices such as the GPU.

The rising popularity of the graphics processing unit (GPU) across various numerical computing applications triggered a breakneck race to optimize key numerical kernels and in particular, the sparse matrix-vector product (SpMV). Despite great strides, most existing GPU-SpMV approaches trade off one aspect of performance against another. They either require preprocessing, exhibit inconsistent behavior, lead to execution divergence, suffer load imbalance or induce detrimental memory access patterns. In this paper, we present an uncompromising approach for SpMV on the GPU. Our approach requires no separate preprocessing or knowledge of the matrix structure and works directly on the standard compressed sparse rows (CSR) data format. From a global perspective, it exhibits a homogeneous behavior reflected in efficient memory access patterns and steady per-thread workload. From a local perspective, it avoids heterogeneous execution paths by adapting its behavior to the work load at hand, it uses an efficient encoding to keep temporary data requirements for on-chip memory low, and leads to divergence-free execution. We evaluate our approach on more than 2500 matrices comparing to vendor provided, and state-of-the-art SpMV implementations. Our approach not only significantly outperforms approaches directly operating on the CSR format ( 20% average performance increase), but also outperforms approaches that preprocess the matrix even when preprocessing time is discarded. Additionally, the same strategies lead to significant performance increase when adapted for transpose SpMV.

In this paper, we show that genetic algorithms (GA) can be used to control the output of procedural modeling algorithms. We propose an efficient way to encode the choices that have to be made during a procedural generation as a hierarchical genome representation. In combination with mutation and reproduction operations specifically designed for controlled procedural modeling, our GA can evolve a population of individual models close to any high-level goal. Possible scenarios include a volume that should be filled by a procedurally grown tree or a painted silhouette that should be followed by the skyline of a procedurally generated city. These goals are easy to set up for an artist compared to the tens of thousands of variables that describe the generated model and are chosen by the GA. Previous approaches for controlled procedural modeling either use Reversible Jump Markov Chain Monte Carlo (RJMCMC) or Stochastically-Ordered Sequential Monte Carlo (SOSMC) as workhorse for the optimization. While RJMCMC converges slowly, requiring multiple hours for the optimization of larger models, it produces high quality models. SOSMC shows faster convergence under tight time constraints for many models, but can get stuck due to choices made in the early stages of optimization. Our GA shows faster convergence than SOSMC and generates better models than RJMCMC in the long run.

Abstract While the modern graphics processing unit (GPU) offers massive parallel compute power, the ability to influence the scheduling of these immense resources is severely limited. Therefore, the GPU is widely considered to be only suitable as an externally controlled co‐processor for homogeneous workloads which greatly restricts the potential applications of GPU computing. To address this issue, we present a new method to achieve fine‐grained priority scheduling on the GPU: hierarchical bucket queuing. By carefully distributing the workload among multiple queues and efficiently deciding which queue to draw work from next, we enable a variety of scheduling strategies. These strategies include fair‐scheduling, earliest‐deadline‐first scheduling and user‐defined dynamic priority scheduling. In a comparison with a sorting‐based approach, we reveal the advantages of hierarchical bucket queuing over previous work. Finally, we demonstrate the benefits of using priority scheduling in real‐world applications by example of path tracing and foveated micropolygon rendering.

Abstract Observing that many visual effects (depth‐of‐field, motion blur, soft shadows, spectral effects) and several sampling modalities (time, stereo or light fields) can be expressed as a sum of many pinhole camera images, we suggest a novel efficient image synthesis framework that exploits coherency among those images. We introduce the notion of “distribution flow” that represents the 2D image deformation in response to changes in the high‐dimensional time‐, lens‐, area light‐, spectral‐, etc. coordinates. Our approach plans the optimal traversal of the distribution space of all required pinhole images, such that starting from one representative root image, which is incrementally changed (warped) in a minimal fashion, pixels move at most by one pixel, if at all. The incremental warping allows extremely simple warping code, typically requiring half a millisecond on an Nvidia Geforce GTX 980Ti GPU per pinhole image. We show, how the bounded sampling does introduce very little errors in comparison to re‐rendering or a common warping‐based solution. Our approach allows efficient previews for arbitrary combinations of distribution effects and imaging modalities with little noise and high visual fidelity.

Abstract In computer vision, convolutional neural networks (CNNs) achieve unprecedented performance for inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer graphics, screen space shading has boosted the quality of real‐time rendering, converting the same kind of attributes of a virtual scene back to appearance, enabling effects like ambient occlusion, indirect light, scattering and many more. In this paper we consider the diagonal problem: synthesizing appearance from given per‐pixel attributes using a CNN. The resulting Deep Shading renders screen space effects at competitive quality and speed while not being programmed by human experts but learned from example images.

This paper proposes a pipeline to accurately acquire, efficiently reproduce and intuitively manipulate phosphorescent appearance. In contrast to common appearance models, a model of phosphorescence needs to account for temporal change (decay) and previous illumination (saturation). For reproduction, we propose a rate equation that can be efficiently solved in combination with other illumination in a mixed integro-differential equation system. We describe an acquisition system to measure spectral coefficients of this rate equation for actual materials. Our model is evaluated by comparison to photographs of actual phosphorescent objects. Finally, we propose an artist-friendly interface to control the behavior of phosphorescent materials by specifying spatiotemporal appearance constraints.

Abstract We propose a method that allows users to define flow features in form of patterns represented as sparse sets of stream line segments. Our approach finds similar occurrences in the same or other time steps. Related approaches define patterns using dense, local stencils or support only single segments. Our patterns are defined sparsely and can have a significant extent, i.e., they are integration‐based and not local. This allows for a greater flexibility in defining features of interest. Similarity is measured using intrinsic curve properties only, which enables invariance to location, orientation, and scale. Our method starts with splitting stream lines using globally consistent segmentation criteria. It strives to maintain the visually apparent features of the flow as a collection of stream line segments. Most importantly, it provides similar segmentations for similar flow structures. For user‐defined patterns of curve segments, our algorithm finds similar ones that are invariant to similarity transformations. We showcase the utility of our method using different 2D and 3D flow fields.

A key advantage of working with structured grids (e.g., images) is the ability to directly tap into the powerful machinery of linear algebra. This is not much so for unstructured grids where intermediate bookkeeping data structures stand in the way. On modern high performance computing hardware, the conventional wisdom behind these intermediate structures is further challenged by costly memory access, and more importantly by prohibitive memory resources on environments such as graphics hardware. In this paper, we bypass this problem by introducing a sparse matrix representation for unstructured grids which not only reduces the memory storage requirements but also cuts down on the bulk of data movement from global storage to the compute units. In order to take full advantage of the proposed representation, we augment ordinary matrix multiplication by means of action maps, local maps which encode the desired interaction between grid vertices. In this way, geometric computations and topological modifications translate into concise linear algebra operations. In our algorithmic formulation, we capitalize on the nature of sparse matrix-vector multiplication which allows avoiding explicit transpose computation and storage. Furthermore, we develop an efficient vectorization to the demanding assembly process of standard graph and finite element matrices.

Gaze-contingent rendering shows promise in improving perceived quality by providing a better match between image quality and the human visual system requirements. For example, information about fixation allows rendering quality to be reduced in peripheral vision, and the additional resources can be used to improve the quality in the foveal region. Gaze-contingent rendering can also be used to compensate for certain limitations of display devices, such as reduced dynamic range or lack of accommodation cues. Despite this potential and the recent drop in the prices of eye trackers, the adoption of such solutions is hampered by system latency which leads to a mismatch between image quality and the actual gaze location. This is especially apparent during fast saccadic movements when the information about gaze location is significantly delayed, and the quality mismatch can be noticed. To address this problem, we suggest a new way of updating images in gaze-contingent rendering during saccades. Instead of rendering according to the current gaze position, our technique predicts where the saccade is likely to end and provides an image for the new fixation location as soon as the prediction is available. While the quality mismatch during the saccade remains unnoticed due to saccadic suppression, a correct image for the new fixation is provided before the fixation is established. This paper describes the derivation of a model for predicting saccade landing positions and demonstrates how it can be used in the context of gaze-contingent rendering to reduce the influence of system latency on the perceived quality. The technique is validated in a series of experiments for various combinations of display frame rate and eye-tracker sampling rate.

We study the design and optimization of statically sound and materially efficient space structures constructed by connected beams. We propose a systematic computational framework for the design of space structures that incorporates static soundness, approximation of reference surfaces, boundary alignment, and geometric regularity. To tackle this challenging problem, we first jointly optimize node positions and connectivity through a nonlinear continuous optimization algorithm. Next, with fixed nodes and connectivity, we formulate the assignment of beam cross sections as a mixed-integer programming problem with a bilinear objective function and quadratic constraints. We solve this problem with a novel and practical alternating direction method based on linear programming relaxation. The capability and efficiency of the algorithms and the computational framework are validated by a variety of examples and comparisons.

We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with kinematic skeleton fitting. Our novel fully-convolutional pose formulation regresses 2D and 3D joint positions jointly in real time and does not require tightly cropped input frames. A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton. This makes our approach the first monocular RGB method usable in real-time applications such as 3D character control---thus far, the only monocular methods for such applications employed specialized RGB-D cameras. Our method's accuracy is quantitatively on par with the best offline 3D monocular RGB pose estimation methods. Our results are qualitatively comparable to, and sometimes better than, results from monocular RGB-D approaches, such as the Kinect. However, we show that our approach is more broadly applicable than RGB-D solutions, i.e., it works for outdoor scenes, community videos, and low quality commodity RGB cameras.

Light scattering in participating media is a natural phenomenon that is increasingly featured in movies and games, as it is visually pleasing and lends realism to a scene. In art, it may further be used to express a certain mood or emphasize objects. Here, artists often rely on stylization when creating scattering effects, not only because of the complexity of physically correct scattering, but also to increase expressiveness. Little research, however, focuses on artistically influencing the simulation of the scattering process in a virtual 3D scene. We propose novel stylization techniques, enabling artists to change the appearance of single scattering effects such as light shafts. Users can add, remove, or enhance light shafts using occluder manipulation. The colors of the light shafts can be stylized and animated using easily modifiable transfer functions. Alternatively, our system can optimize a light map given a simple user input for a number of desired views in the 3D world. Finally, we enable artists to control the heterogeneity of the underlying medium. Our stylized scattering solution is easy to use and compatible with standard rendering pipelines. It works for animated scenes and can be executed in real time to provide the artist with quick feedback.

We propose a new model-based method to accurately reconstruct human performances captured outdoors in a multi-camera setup. Starting from a template of the actor model, we introduce a new unified implicit representation for both, articulated skeleton tracking and non-rigid surface shape refinement. Our method fits the template to unsegmented video frames in two stages - first, the coarse skeletal pose is estimated, and subsequently non-rigid surface shape and body pose are jointly refined. Particularly for surface shape refinement we propose a new combination of 3D Gaussians designed to align the projected model with likely silhouette contours without explicit segmentation or edge detection. We obtain reconstructions of much higher quality in outdoor settings than existing methods, and show that we are on par with state-of-the-art methods on indoor scenes for which they were designed.

Abstract Light field videos express the entire visual information of an animated scene, but their shear size typically makes capture, processing and display anoff‐lineprocess, i. e., time between initial capture and final display is far from real‐time. In this paper we propose a solution for one of the key bottlenecks in such a processing pipeline, which is a reliable depth reconstruction possibly for many views. This is enabled by a novel correspondence algorithm converting the video streams from a sparse array of off‐the‐shelf cameras into an array of animated depth maps. The algorithm is based on a generalization of the classic multi‐resolution Lucas‐Kanade correspondence algorithm from a pair of images to an entire array. Special inter‐image confidence consolidation allows recovery from unreliable matching in some locations and some views. It can be implemented efficiently in massively parallel hardware, allowing for interactive computations. The resulting depth quality as well as the computation performance compares favorably to other state‐of‐the art light field‐to‐depth approaches, as well as stereo matching techniques. Another outcome of this work is a data set of light field videos that are captured with multiple variants of sparse camera arrays.

Abstract VR headsets and hand‐held devices are not powerful enough to render complex scenes in real‐time. A server can take on the rendering task, but network latency prohibits a good user experience. We present a new image‐based rendering (IBR) architecture for masking the latency. It runs in real‐time even on very weak mobile devices, supports modern game engine graphics, and maintains high visual quality even for large view displacements. We propose a novel server‐sidedual‐viewrepresentation that leverages an optimally‐placed extra view and depth peeling to provide the client with coverage for filling disocclusion holes. This representation is directly rendered in a novel wide‐angle projection with favorable directional parameterization. A new client‐side IBR algorithm uses a pre‐transmitted level‐of‐detail proxy with an encaging simplification and depth‐carving to maintain highly complex geometric detail. We demonstrate our approach with typical VR / mobile gaming applications running on mobile hardware. Our technique compares favorably to competing approaches according to perceptual and numerical comparisons.

Abstract We propose projective blue‐noise patterns that retain their blue‐noise characteristics when undergoing one or multiple projections onto lower dimensional subspaces. These patterns are produced by extending existing methods, such as dart throwing and Lloyd relaxation, and have a range of applications. For numerical integration, our patterns often outperform state‐of‐the‐art stochastic and low‐discrepancy patterns, which have been specifically designed only for this purpose. For image reconstruction, our method outperforms traditional blue‐noise sampling when the variation in the signal is concentrated along one dimension. Finally, we use our patterns to distribute primitives uniformly in 3D space such that their 2D projections retain a blue‐noise distribution.

In this paper, we present the concept of operator graph scheduling for high performance procedural generation on the graphics processing unit (GPU). The operator graph forms an intermediate representation that describes all possible operations and objects that can arise during a specific procedural generation. While previous methods have focused on parallelizing a specific procedural approach, the operator graph is applicable to all procedural generation methods that can be described by a graph, such as L-systems, shape grammars, or stack based generation methods. Using the operator graph, we show that all partitions of the graph correspond to possible ways of scheduling a procedural generation on the GPU, including the scheduling strategies of previous work. As the space of possible partitions is very large, we describe three search heuristics, aiding an optimizer in finding the fastest valid schedule for any given operator graph. The best partitions found by our optimizer increase performance of 8 to 30x over the previous state of the art in GPU shape grammar and L-system generation.

Many different techniques for measuring material appearance have been proposed in the last few years. These have produced large public datasets, which have been used for accurate, data-driven appearance modeling. However, although these datasets have allowed us to reach an unprecedented level of realism in visual appearance, editing the captured data remains a challenge. In this paper, we present an intuitive control space for predictable editing of captured BRDF data, which allows for artistic creation of plausible novel material appearances, bypassing the difficulty of acquiring novel samples. We first synthesize novel materials, extending the existing MERL dataset up to 400 mathematically valid BRDFs. We then design a large-scale experiment, gathering 56,000 subjective ratings on the high-level perceptual attributes that best describe our extended dataset of materials. Using these ratings, we build and train networks of radial basis functions to act as functionals mapping the perceptual attributes to an underlying PCA-based representation of BRDFs. We show that our functionals are excellent predictors of the perceived attributes of appearance. Our control space enables many applications, including intuitive material editing of a wide range of visual properties, guidance for gamut mapping, analysis of the correlation between perceptual attributes, or novel appearance similarity metrics. Moreover, our methodology can be used to derive functionals applicable to classic analytic BRDF representations. We release our code and dataset publicly, in order to support and encourage further research in this direction.

Binocular disparity is the main depth cue that makes stereoscopic images appear 3D. However, in many scenarios, the range of depth that can be reproduced by this cue is greatly limited and typically fixed due to constraints imposed by displays. For example, due to the low angular resolution of current automultiscopic screens, they can only reproduce a shallow depth range. In this work, we study the motion parallax cue, which is a relatively strong depth cue, and can be freely reproduced even on a 2D screen without any limits. We exploit the fact that in many practical scenarios, motion parallax provides sufficiently strong depth information that the presence of binocular depth cues can be reduced through aggressive disparity compression. To assess the strength of the effect we conduct psycho-visual experiments that measure the influence of motion parallax on depth perception and relate it to the depth resulting from binocular disparity. Based on the measurements, we propose a joint disparity-parallax computational model that predicts apparent depth resulting from both cues. We demonstrate how this model can be applied in the context of stereo and multiscopic image processing, and propose new disparity manipulation techniques, which first quantify depth obtained from motion parallax, and then adjust binocular disparity information accordingly. This allows us to manipulate the disparity signal according to the strength of motion parallax to improve the overall depth reproduction. This technique is validated in additional experiments.

Producing a high quality stereoscopic impression on current displays is a challenging task. The content has to be carefully prepared in order to maintain visual comfort, which typically affects the quality of depth reproduction. In this work, we show that this problem can be significantly alleviated when the eye fixation regions can be roughly estimated. We propose a new method for stereoscopic depth adjustment that utilizes eye tracking or other gaze prediction information. The key idea that distinguishes our approach from the previous work is to apply gradual depth adjustments at the eye fixation stage, so that they remain unnoticeable. To this end, we measure the limits imposed on the speed of disparity changes in various depth adjustment scenarios, and formulate a new model that can guide such seamless stereoscopic content processing. Based on this model, we propose a real-time controller that applies local manipulations to stereoscopic content to find the optimum between depth reproduction and visual comfort. We show that the controller is mostly immune to the limitations of low-cost eye tracking solutions. We also demonstrate benefits of our model in off-line applications, such as stereoscopic movie production, where skillful directors can reliably guide and predict viewers' attention or where attended image regions are identified during eye tracking sessions. We validate both our model and the controller in a series of user experiments. They show significant improvements in depth perception without sacrificing the visual quality when our techniques are applied.

Marker-based and marker-less optical skeletal motion-capture methods use an outside-in arrangement of cameras placed around a scene, with viewpoints converging on the center. They often create discomfort with marker suits, and their recording volume is severely restricted and often constrained to indoor scenes with controlled backgrounds. Alternative suit-based systems use several inertial measurement units or an exoskeleton to capture motion with an inside-in setup, i.e. without external sensors. This makes capture independent of a confined volume, but requires substantial, often constraining, and hard to set up body instrumentation. Therefore, we propose a new method for real-time, marker-less, and egocentric motion capture: estimating the full-body skeleton pose from a lightweight stereo pair of fisheye cameras attached to a helmet or virtual reality headset - an optical inside-in method, so to speak. This allows full-body motion capture in general indoor and outdoor scenes, including crowded scenes with many people nearby, which enables reconstruction in larger-scale activities. Our approach combines the strength of a new generative pose estimation framework for fisheye views with a ConvNet-based body-part detector trained on a large new dataset. It is particularly useful in virtual reality to freely roam and interact, while seeing the fully motion-captured virtual body.

The visual quality of a motion picture is significantly influenced by the choice of the presentation frame rate. Increasing the frame rate improves the clarity of the image and helps to alleviate many artifacts, such as blur, strobing, flicker, or judder. These benefits, however, come at the price of losing well-established film aesthetics, often referred to as the "cinematic look". Current technology leaves artists with a sparse set of choices, e.g., 24 Hz or 48 Hz, limiting the freedom in adjusting the frame rate to artistic needs, content, and display technology. In this paper, we solve this problem by proposing a novel filtering technique which enables emulating the whole spectrum of presentation frame rates on a single-frame-rate display. The key component of our technique is a set of simple yet powerful filters calibrated and evaluated in psychophysical experiments. By varying their parameters we can achieve an impression of continuously varying presentation frame rate in both the spatial and temporal dimensions. This allows artists to achieve the best balance between the aesthetics and the objective quality of the motion picture. Furthermore, we show how our technique, informed by cinematic guidelines, can adapt to the content and achieve this balance automatically.

We present an approach to pattern matching in 3D multi-field scalar data. Existing pattern matching algorithms work on single scalar or vector fields only, yet many numerical simulations output multi-field data where only a joint analysis of multiple fields describes the underlying phenomenon fully. Our method takes this into account by bundling information from multiple fields into the description of a pattern. First, we extract a sparse set of features for each 3D scalar field using the 3D SIFT algorithm (Scale-Invariant Feature Transform). This allows for a memory-saving description of prominent features in the data with invariance to translation, rotation, and scaling. Second, the user defines a pattern as a set of SIFT features in multiple fields by e.g. brushing a region of interest. Third, we locate and rank matching patterns in the entire data set. Experiments show that our algorithm is efficient in terms of required memory and computational efforts.

This paper addresses approximate partial symmetry detection in 3D point clouds, a classical and foundational tool for analyzing geometry. We present a novel, fully unsupervised method that detects partial symmetry under significant geometric variability, and without constraints on the number and arrangement of instances. The core idea is a matching scheme that finds consistent co-occurrence patterns in a frame-invariant way. We obtain a canonical partition of the input shape into building blocks and can handle ambiguous data by aggregating co-occurrence information across both all building block instances and the area they cover. We evaluate our method on several benchmark data sets and demonstrate its significant improvements in handling geometric variability, including scanning noise, irregular patterns, appearance variation and shape deformation.

Different from classic reconstruction of physical depth in computer vision, depth for 2D-to-3D stereo conversion is assigned by humans using semi-automatic painting interfaces and, consequently, is often dramatically wrong. Here we seek to better understand why it still does not fail to convey a sensation of depth. To this end, four typical disparity distortions resulting from manual 2D-to-3D stereo conversion are analyzed: i) smooth remapping, ii) spatial smoothness, iii) motion-compensated, temporal smoothness, and iv) completeness. A perceptual experiment is conducted to quantify the impact of each distortion on the plausibility of the 3D impression relative to a reference without distortion. Close-to-natural videos with known depth were distorted in one of the four above-mentioned aspects and subjects had to indicate if the distortion still allows for a plausible 3D effect. The smallest amounts of distortion that result in a significant rejection suggests a conservative upper bound on the quality requirement of 2D-to-3D conversion.

Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images. Proper handling of occlusions is a big challenge, since the visibility function that indicates if a surface point is seen from a camera can often not be formulated in closed form, and is in general discrete and non-differentiable at occlusion boundaries. We present a new scene representation that enables an analytically differentiable closed-form formulation of surface visibility. In contrast to previous methods, this yields smooth, analytically differentiable, and efficient to optimize pose similarity energies with rigorous occlusion handling, fewer local minima, and experimentally verified improved convergence of numerical optimization. The underlying idea is a new image formation model that represents opaque objects by a translucent medium with a smooth Gaussian density distribution which turns visibility into a smooth phenomenon. We demonstrate the advantages of our versatile scene model in several generative pose estimation problems, namely marker-less multi-object pose estimation, marker-less human motion capture with few cameras, and image-based 3D geometry estimation.

Abstract Providing multiple meanings in a single piece of art has always been intriguing to both artists and observers. We present Purkinje images, which have different interpretations depending on the luminance adaptation of the observer. Finding such images is an optimization that minimizes the sum of the distance to one reference image in photopic conditions and the distance to another reference image in scotopic conditions. To model the shift of image perception between day and night vision, we decompose the input images into a Laplacian pyramid. Distances under different observation conditions in this representation are independent between pyramid levels and pixel positions and become matrix multiplications. The optimal pixel colour can be found by inverting a small, per‐pixel linear system in real time on a GPU. Finally, two user studies analyze our results in terms of the recognition performance and fidelity with respect to the reference images.

Abstract Splines are part of the standard toolbox for the approximation of functions and curves in ℝd. Still, the problem of finding the spline that best approximates an input function or curve is ill‐posed, since in general this yields a “spline” with an infinite number of segments. The problem can be regularized by adding a penalty term for the number of spline segments. We show how this idea can be formulated as an ℓ0‐regularized quadratic problem. This gives us a notion of optimal approximating splines that depend on one parameter, which weights the approximation error against the number of segments. We detail this concept for different types of splines including B‐splines and composite Bézier curves. Based on the latest development in the field of sparse approximation, we devise a solver for the resulting minimization problems and show applications to spline approximation of planar and space curves and to spline conversion of motion capture data.

Abstract Mobile phones and tablets are rapidly gaining significance as omnipresent image and video capture devices. In this context we present an algorithm that allows such devices to capture high dynamic range (HDR) video. The design of the algorithm was informed by a perceptual study that assesses the relative importance of motion and dynamic range. We found that ghosting artefacts are more visually disturbing than a reduction in dynamic range, even if a comparable number of pixels is affected by each. We incorporated these findings into a real‐time, adaptive metering algorithm that seamlessly adjusts its settings to take exposures that will lead to minimal visual artefacts after recombination into an HDR sequence. It is uniquely suitable for real‐time selection of exposure settings. Finally, we present an off‐line HDR reconstruction algorithm that is matched to the adaptive nature of our real‐time metering approach.

Abstract In this paper, we propose a new method for structuring multi‐modal representations of shapes according to semantic relations. We learn a metric that links semantically similar objects represented in different modalities. First, 3D‐shapes are associated with textual labels by learning how textual attributes are related to the observed geometry. Correlations between similar labels are captured by simultaneously embedding labels and shape descriptors into a common latent space in which an inner product corresponds to similarity. The mapping is learned robustly by optimizing a rank‐based loss function under a sparseness prior for the spectrum of the matrix of all classifiers. Second, we extend this framework towards relating multi‐modal representations of the geometric objects. The key idea is that weak cues from shared human labels are sufficient to obtain a consistent embedding of related objects even though their representations are not directly comparable. We evaluate our method against common base‐line approaches, investigate the influence of different geometric descriptors, and demonstrate a prototypical multi‐modal browser that relates 3D‐objects with text, photographs, and 2D line sketches.

Abstract When human luminance perception operates close to its absolute threshold, i. e., the lowest perceivable absolute values, appearance changes substantially compared to common photopic or scotopic vision. In particular, most observers report perceiving temporally‐varying noise. Two reasons are physiologically plausible; quantum noise (due to the low absolute number of photons) and spontaneous photochemical reactions. Previously, static noise with a normal distribution and no account for absolute values was combined with blue hue shift and blur to simulate scotopic appearance on a photopic display for movies and interactive applications (e.g., games). We present a computational model to reproduce the specific distribution and dynamics of “scotopic noise” for specific absolute values. It automatically introduces a perceptually‐calibrated amount of noise for a specific luminance level and supports animated imagery. Our simulation runs in milliseconds at HD resolution using graphics hardware and favorably compares to simpler alternatives in a perceptual experiment.

Abstract We propose a system to restrict the manipulation of shape and appearance in an image to a valid subspace which we learn from a collection of exemplar images. To this end, we automatically co‐align a collection of images and learn a subspace model of shape and appearance using principal components. As finding perfect image correspondences for general images is not feasible, we build an approximate partial alignment and improve bad alignments leveraging other, more successful alignments. Our system allows the user to change appearance and shape in real‐time and the result is “projected” onto the subspace of meaningful changes. The change in appearance and shape can either be locked or performed independently. Additional applications include suggestion of alternative shapes or appearance.

Color selection is required in many computer graphics applications, but can be tedious, as 1D or 2D user interfaces are employed to navigate in a 3D color space. Until now the problem was considered a question of designing general color spaces with meaningful (e.g., perceptual) parameters. In this work, we show how color selection usability improves by applying 1D or 2D color manifolds that predict the most likely change of color in a specific context. A typical use-case is manipulating the color of a banana; instead of presenting a 2D+1D RGB, CIE Lab, or HSV widget, our approach presents a simple 1D slider that captures the most likely change for this context. Technically, for each context, we learn a lower-dimensional manifold with varying density from labeled Internet examples. We demonstrate the increase in task performance of color selection in a user study.

Motion-tracked real-time character control is important for games and VR, but current solutions are limited: retargeting is hard for non-human characters, with locomotion bound to the sensing volume; and pose mappings are ambiguous with difficult dynamic motion control. We robustly estimate wave properties --- amplitude, frequency, and phase ---for a set of interactively-defined gestures by mapping user motions to a low-dimensional independent representation. The mapping separates simultaneous or intersecting gestures, and extrapolates gesture variations from single training examples. For animations such as locomotion, wave properties map naturally to stride length, step frequency, and progression, and allow smooth transitions from standing, to walking, to running. Interpolating out-of-phase locomotions is hard, e.g., quadruped legs between walks and runs switch phase, so we introduce a new time-interpolation scheme to reduce artifacts. These improvements to real-time motion-tracked character control are important for common cyclic animations. We validate this in a user study, and show versatility to apply to part- and full-body motions across a variety of sensors.

We introduce a scheme for real-time nonlinear interpolation of a set of shapes. The scheme exploits the structure of the shape interpolation problem, in particular the fact that the set of all possible interpolated shapes is a low-dimensional object in a high-dimensional shape space. The interpolated shapes are defined as the minimizers of a nonlinear objective functional on the shape space. Our approach is to construct a reduced optimization problem that approximates its unreduced counterpart and can be solved in milliseconds. To achieve this, we restrict the optimization to a low-dimensional subspace that is specifically designed for the shape interpolation problem. The construction of the subspace is based on two components: a formula for the calculation of derivatives of the interpolated shapes and a Krylov-type sequence that combines the derivatives and the Hessian of the objective functional. To make the computational cost for solving the reduced optimization problem independent of the resolution of the example shapes, we combine the dimensional reduction with schemes for the efficient approximation of the reduced nonlinear objective functional and its gradient. In our experiments, we obtain rates of 20--100 interpolated shapes per second, even for the largest examples which have 500k vertices per example shape.

Real-time marker-less hand tracking is of increasing importance in human-computer interaction. Robust and accurate tracking of arbitrary hand motion is a challenging problem due to the many degrees of freedom, frequent self-occlusions, fast motions, and uniform skin color. In this paper, we propose a new approach that tracks the full skeleton motion of the hand from multiple RGB cameras in real-time. The main contributions include a new generative tracking method which employs an implicit hand shape representation based on Sum of Anisotropic Gaussians (SAG), and a pose fitting energy that is smooth and analytically differentiable making fast gradient based pose optimization possible. This shape representation, together with a full perspective projection model, enables more accurate hand modeling than a related baseline method from literature. Our method achieves better accuracy than previous methods and runs at 25 fps. We show these improvements both qualitatively and quantitatively on publicly available datasets.

Texture synthesis is a versatile tool for creating and editing 2D images. However, applying it to 3D content creation is difficult due to the higher demand of model accuracy and the large search space that also contains many implausible shapes. Our paper explores offset statistics for 3D shape retargeting. We observe that the offset histograms between similar 3D features are sparse, in particular for man-made objects such as buildings and furniture. We employ sparse offset statistics to improve 3D shape retargeting (i.e., Rescaling in different directions). We employ a graph-cut texture synthesis method that iteratively stitches model fragments shifted by the detected sparse offsets. The offsets reveal important structural redundancy which leads to more plausible results and more efficient optimization. Our method is fully automatic, while intuitive user control can be incorporated for interactive modeling in real-time. We empirically evaluate the sparsity of offset statistics across a wide range of subjects, and show our statistics based retargeting significantly improves quality and efficiency over conventional MRF models.

Many people who first see a high dynamic range (HDR) display get the impression that it is a 3D display, even though it does not produce any binocular depth cues. Possible explanations of this effect include contrast-based depth induction and the increased realism due to the high brightness and contrast that makes an HDR display "like looking through a window". In this paper we test both of these hypotheses by comparing the HDR depth illusion to real binocular depth cues using a carefully calibrated HDR stereoscope. We confirm that contrast-based depth induction exists, but it is a vanishingly weak depth cue compared to binocular depth cues. We also demonstrate that for some observers, the increased contrast of HDR displays indeed increases the realism. However, it is highly observer-dependent whether reduced, physically correct, or exaggerated contrast is perceived as most realistic, even in the presence of the real-world reference scene. Similarly, observers differ in whether reduced, physically correct, or exaggerated stereo 3D is perceived as more realistic. To accommodate the binocular depth perception and realism concept of most observers, display technologies must offer both HDR contrast and stereo personalization.

Parallel Coordinates is an often used visualization method for multidimensional data sets. Its main challenges for large data sets are visual clutter and over plotting which hamper the recognition of patterns in the data. We present an edge-bundling method using density-based clustering for each dimension. This reduces clutter and provides a faster overview of clusters and trends. Moreover, it allows rendering the clustered lines using polygons, decreasing rendering time remarkably. In addition, we design interactions to support multidimensional clustering with this method. A user study shows improvements over the classic parallel coordinates plot in two user tasks: correlation estimation and subset tracing.

Volumetric light scattering is a complex phenomenon that is difficult to simulate in real time as light can be scattered towards the camera from everywhere in space. By assuming a single-scattering model, we can transform the usually-employed ray-marching into an efficient ray-independent texture filtering process. Our algorithm builds upon a rectified shadow map as input and we propose an efficient rectification scheme, which could be used by other approaches as well. The resulting scattering method is very fast and almost independent of the screen resolution, but it still produces near-reference results. These properties make it a good candidate for performance-critical applications, such as games.

Computing shading such as ambient occlusion (AO), subsurface scattering (SSS) or indirect light (GI) in screen space has recently received a lot of attention. While being efficient to compute, screen space methods have several key limitations such as occlusions, culling, under-sampling of oblique geometry and locality of the transport. In this work we propose a deep screen space to overcome all these problems while retaining computational efficiency. Instead of projecting, culling, shading, rasterizing and resolving occlusions of primitives using a z-buffer, we adaptively tessellate them into surfels proportional to the primitive's projected size, which are optionally shaded and stored on-GPU as an unstructured surfel cloud. Objects closer to the camera receive more details, like in classic framebuffers, but are not affected by occlusions or viewing angle. This surfel cloud can then be used to compute shading. Instead of gathering, we propose to use splatting to a multi-resolution interleaved framebuffer. This allows to exchange detailed shading between pixels close to a surfel and approximate shading between pixels distant to a surfel.

Abstract Presenting stereoscopic content on 3D displays is a challenging task, usually requiring manual adjustments. A number of techniques have been developed to aid this process, but they account for binocular disparity of surfaces that are diffuse and opaque only. However, combinations of transparent as well as specular materials are common in the real and virtual worlds, and pose a significant problem. For example, excessive disparities can be created which cannot be fused by the observer. Also, multiple stereo interpretations become possible, e. g., for glass, that both reflects and refracts, which may confuse the observer and result in poor 3D experience. In this work, we propose an efficient method for analyzing and controlling disparities in computer‐generated images of such scenes where surface positions and a layer decomposition are available. Instead of assuming a single per‐pixel disparity value, we estimate all possibly perceived disparities at each image location. Based on this representation, we define an optimization to find the best per‐pixel camera parameters, assuring that all disparities can be easily fused by a human. A preliminary perceptual study indicates, that our approach combines comfortable viewing with realistic depiction of typical specular scenes.

Abstract Light refracted by a dispersive interface leads to beautifully colored patterns that can be rendered faithfully with spectral Monte‐Carlo methods. Regrettably, results often suffer from chromatic noise or banding, requiring high sampling rates and large amounts of memory compared to renderers operating in some trichromatic color space. Addressing this issue, we introduce spectral ray differentials, which describe the change of light direction with respect to changes in the spectrum. In analogy with the classic ray and photon differentials, this information can be used for filtering in the spectral domain. Effectiveness of our approach is demonstrated by filtering for offline spectral light and path tracing as well as for an interactive GPU photon mapper based on splatting. Our results show considerably less chromatic noise and spatial aliasing while retaining good visual similarity to reference solutions with negligible overhead in the order of milliseconds.

Abstract Image calibration requires both linearization of pixel values and scaling so that values in the image correspond to real‐world luminances. In this paper we focus on the latter and rather than rely on camera characterization, we calibrate images by analysing their content and metadata, obviating the need for expensive measuring devices or modeling of lens and camera combinations. Our analysis correlates sky pixel values to luminances that would be expected based on geographical metadata. Combined with high dynamic range (HDR) imaging, which gives us linear pixel data, our algorithm allows us to find absolute luminance values for each pixel—effectively turning digital cameras into absolute light meters. To validate our algorithm we have collected and annotated a calibrated set of HDR images and compared our estimation with several other approaches, showing that our approach is able to more accurately recover absolute luminance. We discuss various applications and demonstrate the utility of our method in the context of calibrated color appearance reproduction and lighting design.

Abstract In this paper, we propose a new method for reconstructing 3D models from a noisy and incomplete 3D scan and a coarse template model. The main idea is to maintain characteristic high‐level features of the template that remain unchanged for different variants of the same type of object. As invariants, we chose the partial symmetry structure of the template model under Euclidian transformations, i.e. we maintain the algebraic structure of all reflections, rotations and translations that map the object partially to itself. We propose an optimization scheme that maintains continuous and discrete symmetry properties of this kind while registering a template against scan data using a deformable iterative closest points (ICP) framework with thin‐plate‐spline regularization. We apply our new deformation approach to a large number of example data sets and demonstrate that symmetry‐guided template matching often yields much more plausible reconstructions than previous variants of ICP.

Abstract It is now possible to capture the 3D motion of the human body on consumer hardware and to puppet in real time skeleton‐based virtual characters. However, many characters do not have humanoid skeletons. Characters such as spiders and caterpillars do not have boned skeletons at all, and these characters have very different shapes and motions. In general, character control under arbitrary shape and motion transformations is unsolved ‐ how might these motions be mapped? We control characters with a method which avoids the rigging‐skinning pipeline — source and target characters do not have skeletons or rigs. We use interactively‐defined sparse pose correspondences to learn a mapping between arbitrary 3D point source sequences and mesh target sequences. Then, we puppet the target character in real time. We demonstrate the versatility of our method through results on diverse virtual characters with different input motion controllers. Our method provides a fast, flexible, and intuitive interface for arbitrary motion mapping which provides new ways to control characters for real‐time animation.

Abstract We present a method to find repeating topological structures in scalar data sets. More precisely, we compare all subtrees of two merge trees against each other – in an efficient manner exploiting redundancy. This provides pair‐wise distances between the topological structures defined by sub/superlevel sets, which can be exploited in several applications such as finding similar structures in the same data set, assessing periodic behavior in time‐dependent data, and comparing the topology of two different data sets. To do so, we introduce a novel data structure called theextended branch decomposition graph, which is composed of the branch decompositions of all subtrees of the merge tree. Based on dynamic programming, we provide two highly efficient algorithms for computing and comparing extended branch decomposition graphs. Several applications attest to the utility of our method and its robustness against noise.

Abstract Stream surfaces are a well‐studied and widely used tool for the visualization of 3D flow fields. Usually, stream surface seeding is carried out manually in time‐consuming trial and error procedures. Only recently automatic selection methods were proposed. Local methods support the selection of a set of stream surfaces, but, contrary to global selection methods, they evaluate only thequalityof the seeding lines but not the quality of the whole stream surfaces. Global methods, on the other hand, only support the selection of asingleoptimal stream surface until now. However, for certain flow fields a single stream surface is not sufficient to represent all flow features. In our work, we overcome this limitation by introducing a global selection technique for asetof stream surfaces. All selected surfaces optimize global stream surface quality measures and are guaranteed to be mutually distant, such that they can convey different flow features. Our approach is an efficient extension of the most recent global selection method for single stream surfaces. We illustrate its effectiveness on a number of analytical and simulated flow fields and analyze the quality of the results in a user study.

Abstract Independent management of film grain in each view of a stereoscopic video can lead to visual discomfort. The existing alternative is to project the grain onto the scene geometry. Such grain, however, looks unnatural, changes object perception, and emphasizes inaccuracies in depth arising during 2D‐to‐3D conversion. We propose an advanced method of grain positioning that scatters the grain in the scene space. In a series of perceptual experiments, we estimate the optimal parameter values for the proposed method, analyze the user preference distribution among the proposed and the two existing methods, and show influence of the method on the object perception.

Abstract In this paper, we address the problem of structure‐aware shape deformation: We specifically consider deformations that preserve symmetries of the shape being edited. While this is an elegant approach for obtaining plausible shape variations from minimal assumptions, a straightforward optimization is numerically expensive and poorly conditioned. Our paper introduces an explicit construction of bases of linear spaces of shape deformations that exactly preserve symmetries for any user‐defined level of detail. This permits the construction of low‐dimensional spaces of low‐frequency deformations that preserve the symmetries. We obtain substantial speed‐ups over alternative approaches for symmetry‐preserving shape editing due to (i) the sub‐space approach, which permits low‐res editing, (ii) the removal of redundant, symmetric information, and (iii) the simplification of the numerical formulation due to hard‐coded symmetry preservation. We demonstrate the utility in practice by applying our framework to symmetry‐preserving co‐rotated iterative Laplace surface editing of models with complex symmetry structure, including partial and nested symmetry.

Several approaches attempt to reproduce the appearance of a scotopic low-light night scene on a photopic display (“day-for-night”) by introducing color desaturation, loss of acuity, and the Purkinje shift toward blue colors. We argue that faithful stereo reproduction of night scenes on photopic stereo displays requires manipulation of not only color but also binocular disparity. To this end, we performed a psychophysics experiment to devise a model of disparity at scotopic luminance levels. Using this model, we can match binocular disparity of a scotopic stereo content displayed on a photopic monitor to the disparity that would be perceived if the scene was actually scotopic. The model allows for real-time computation of common stereo content as found in interactive applications such as simulators or computer games.

Sudden temporal depth changes, such as cuts that are introduced by video edits, can significantly degrade the quality of stereoscopic content. Since usually not encountered in the real world, they are very challenging for the audience. This is because the eye vergence has to constantly adapt to new disparities in spite of conflicting accommodation requirements. Such rapid disparity changes may lead to confusion, reduced understanding of the scene, and overall attractiveness of the content. In most cases the problem cannot be solved by simply matching the depth around the transition, as this would require flattening the scene completely. To better understand this limitation of the human visual system, we conducted a series of eye-tracking experiments. The data obtained allowed us to derive and evaluate a model describing adaptation of vergence to disparity changes on a stereoscopic display. Besides computing user-specific models, we also estimated parameters of an average observer model. This enables a range of strategies for minimizing the adaptation time in the audience.

We propose a scheme for animating deformable objects based on spacetime optimization. The main feature is that it robustly and within a few seconds generates interesting motion from a sparse set of spacetime constraints. Providing only partial (as opposed to full) keyframes for positions and velocities is sufficient. The computed motion satisfies the constraints and the remaining degrees of freedom are determined by physical principles using elasticity and the spacetime constraints paradigm. Our modeling of the spacetime optimization problem combines dimensional reduction, modal coordinates, wiggly splines, and rotation strain warping. Our solver is based on a theorem that characterizes the solutions of the optimization problem and allows us to restrict the optimization to low-dimensional search spaces. This treatment of the optimization problem avoids a time discretization and the resulting method can robustly deal with sparse input and wiggly motion.

In this paper we address the problem of finding correspondences between related shapes of widely varying geometry. We propose a new method based on the observation that symmetry and regularity in shapes is often associated with their function. Hence, they provide cues for matching related geometry even under strong shape variations. Correspondingly, we decomposes shapes into overlapping regions determined by their regularity properties. Afterwards, we form a graph that connects these pieces via pairwise relations that capture geometric relations between rotation axes and reflection planes as well as topological or proximity relations. Finally, we perform graph matching to establish correspondences. The method yields certain more abstract but semantically meaningful correspondences between man-made shapes that are too difficult to recognize by traditional geometric methods.

Data acquisition, numerical inaccuracies, and sampling often introduce noise in measurements and simulations. Removing this noise is often necessary for efficient analysis and visualization of this data, yet many denoising techniques change the minima and maxima of a scalar field. For example, the extrema can appear or disappear, spatially move, and change their value. This can lead to wrong interpretations of the data, e.g., when the maximum temperature over an area is falsely reported being a few degrees cooler because the denoising method is unaware of these features. Recently, a topological denoising technique based on a global energy optimization was proposed, which allows the topology-controlled denoising of 2D scalar fields. While this method preserves the minima and maxima, it is constrained by the size of the data. We extend this work to large 2D data and medium-sized 3D data by introducing a novel domain decomposition approach. It allows processing small patches of the domain independently while still avoiding the introduction of new critical points. Furthermore, we propose an iterative refinement of the solution, which decreases the optimization energy compared to the previous approach and therefore gives smoother results that are closer to the input. We illustrate our technique on synthetic and real-world 2D and 3D data sets that highlight potential applications.

Although volumetric phenomena are important for realistic rendering and can even be a crucial component in the image, the artistic control of the volume's appearance is challenging. Appropriate tools to edit volume properties are missing, which can make it necessary to use simulation results directly. Alternatively, high-level modifications that are rarely intuitive, e.g., the tweaking of noise function parameters, can be utilized. Our work introduces a solution to stylize single-scattering volumetric effects in static volumes. Hereby, an artistic and intuitive control of emission, scattering and extinction becomes possible, while ensuring a smooth and coherent appearance when changing the viewpoint. Our method is based on tomographic reconstruction, which we link to the volumetric rendering equation. It analyzes a number of target views provided by the artist and adapts the volume properties to match the appearance for the given perspectives. Additionally, we describe how we can optimize for the environmental lighting to match a desired scene appearance, while keeping volume properties constant. Finally, both techniques can be combined. We demonstrate several use cases of our approach and illustrate its effectiveness.

In Human-Computer Interaction (HCI), experts seek to evaluate and compare the performance and ergonomics of user interfaces. Recently, a novel cost-efficient method for estimating physical ergonomics and performance has been introduced to HCI. It is based on optical motion capture and biomechanical simulation. It provides a rich source for analyzing human movements summarized in a multidimensional data set. Existing visualization tools do not sufficiently support the HCI experts in analyzing this data. We identified two shortcomings. First, appropriate visual encodings are missing particularly for the biomechanical aspects of the data. Second, the physical setup of the user interface cannot be incorporated explicitly into existing tools. We present MovExp, a versatile visualization tool that supports the evaluation of user interfaces. In particular, it can be easily adapted by the HCI experts to include the physical setup that is being evaluated, and visualize the data on top of it. Furthermore, it provides a variety of visual encodings to communicate muscular loads, movement directions, and other specifics of HCI studies that employ motion capture and biomechanical simulation. In this design study, we follow a problem-driven research approach. Based on a formalization of the visualization needs and the data structure, we formulate technical requirements for the visualization tool and present novel solutions to the analysis needs of the HCI experts. We show the utility of our tool with four case studies from the daily work of our HCI experts.

Reconstructing a three-dimensional representation of human motion in real-time constitutes an important research topic with applications in sports sciences, human-computer-interaction, and the movie industry. In this paper, we contribute with a robust algorithm for estimating a personalized human body model from just two sequentially captured depth images that is more accurate and runs an order of magnitude faster than the current state-of-the-art procedure. Then, we employ the estimated body model to track the pose in real-time from a stream of depth images using a tracking algorithm that combines local pose optimization and a stabilizing dataBase look-up. Together, this enables accurate pose tracking that is more accurate than previous approaches. As a further contribution, we evaluate and compare our algorithm to previous work on a comprehensive benchmark dataset containing more than 15 minutes of challenging motions. This dataset comprises calibrated marker-Based motion capture data, depth data, as well as ground truth tracking results and is publicly available for research purposes.

This paper presents a semi-automatic method to fit a template mesh to high-resolution normal data, which is generated using spherical gradient illuminations in a light stage. Template fitting is an important step to build a 3D morph able face model, which can be employed for image-Based facial performance capturing. In contrast to existing 3D reconstruction approaches, we omit the structured light scanning step to obtain low-frequency 3D information and rely solely on normal data from multiple views. This reduces the acquisition time by over 50 percent. In our experiments the proposed algorithm is successfully applied to real faces of several subjects. Experiments with synthetic data show that the fitted face template can closely resemble the ground truth geometry.

We investigate the problem of identifying the position of a viewer inside a room of planar mirrors with unknown geometry in conjunction with the room's shape parameters. We consider the observations to consist of angularly resolved depth measurements of a single scene point that is being observed via many multi-bounce interactions with the specular room geometry. Applications of this problem statement include areas such as calibration, acoustic echo cancelation and time-of-flight imaging. We theoretically analyze the problem and derive sufficient conditions for a combination of convex room geometry, observer, and scene point to be reconstruct able. The resulting constructive algorithm is exponential in nature and, therefore, not directly applicable to practical scenarios. To counter the situation, we propose theoretically devised geometric constraints that enable an efficient pruning of the solution space and develop a heuristic randomized search algorithm that uses these constraints to obtain an effective solution. We demonstrate the effectiveness of our algorithm on extensive simulations as well as in a challenging real-world calibration scenario.

In recent years, the availability of inexpensive depth cameras, such as the Microsoft Kinect, has boosted the research in monocular full body skeletal pose tracking. Unfortunately, existing trackers often fail to capture poses where a single camera provides insufficient data, such as non-frontal poses, and all other poses with body part occlusions. In this paper, we present a novel sensor fusion approach for real-time full body tracking that succeeds in such difficult situations. It takes inspiration from previous tracking solutions, and combines a generative tracker and a discriminative tracker retrieving closest poses in a database. In contrast to previous work, both trackers employ data from a low number of inexpensive body-worn inertial sensors. These sensors provide reliable and complementary information when the monocular depth information alone is not sufficient. We also contribute by new algorithmic solutions to best fuse depth and inertial data in both trackers. One is a new visibility model to determine global body pose, occlusions and usable depth correspondences and to decide what data modality to use for discriminative tracking. We also contribute with a new inertial-based pose retrieval, and an adapted late fusion step to calculate the final body pose.

Face detection is an important task in computer vision and often serves as the first step for a variety of applications. State-of-the-art approaches use efficient learning algorithms and train on large amounts of manually labeled imagery. Acquiring appropriate training images, however, is very time-consuming and does not guarantee that the collected training data is representative in terms of data variability. Moreover, available data sets are often acquired under controlled settings, restricting, for example, scene illumination or 3D head pose to a narrow range. This paper takes a look into the automated generation of adaptive training samples from a 3D morphable face model. Using statistical insights, the tailored training data guarantees full data variability and is enriched by arbitrary facial attributes such as age or body weight. Moreover, it can automatically adapt to environmental constraints, such as illumination or viewing angle of recorded video footage from surveillance cameras. We use the tailored imagery to train a new many-core implementation of Viola Jones' AdaBoost object detection framework. The new implementation is not only faster but also enables the use of multiple feature channels such as color features at training time. In our experiments we trained seven view-dependent face detectors and evaluate these on the Face Detection Data Set and Benchmark (FDDB). Our experiments show that the use of tailored training imagery outperforms state-of-the-art approaches on this challenging dataset.

Volumetric phenomena are an integral part of standard rendering, yet, no suitable tools to edit characteristic properties are available so far. Either simulation results are used directly, or modifications are high-level, e.g., noise functions to influence appearance. Intuitive artistic control is not possible.

Abstract In this work, we present an analysis of feature descriptors for objective image quality assessment. We explore a large space of possible features including components of existing image quality metrics as well as many traditional computer vision and statistical features. Additionally, we propose new features motivated by human perception and we analyze visual saliency maps acquired using an eye tracker in our user experiments. The discriminative power of the features is assessed by means of a machine learning framework revealing the importance of each feature for image quality assessment task. Furthermore, we propose a new data‐driven full‐reference image quality metric which outperforms current state‐of‐theart metrics. The metric was trained on subjective ground truth data combining two publicly available datasets. For the sake of completeness we create a new testing synthetic dataset including experimentally measured subjective distortion maps. Finally, using the same machine‐learning framework we optimize the parameters of popular existing metrics.

Abstract Beyond the careful design of stereo acquisition equipment and rendering algorithms, disparity post‐processing has recently received much attention, where one of the key tasks is to compress the originally large disparity range to avoid viewing discomfort. The perception of dynamic stereo content however, relies on reproducing the full disparity‐time volume that a scene point undergoes in motion. This volume can be strongly distorted in manipulation, which is only concerned with changing disparity at one instant in time, even if the temporal coherence of that change is maintained. We propose an optimization to preserve stereo motion of content that was subject to an arbitrary disparity manipulation, based on a perceptual model of temporal disparity changes. Furthermore, we introduce a novel 3D warping technique to create stereo image pairs that conform to this optimized disparity map. The paper concludes with perceptual studies of motion reproduction quality and task performance in a simple game, showing how our optimization can achieve both viewing comfort and faithful stereo motion.

Abstract In this paper, we present a novel method for detecting partial symmetries in very large point clouds of 3D city scans. Unlike previous work, which has only been demonstrated on data sets of a few hundred megabytes maximum, our method scales to very large scenes: We map the detection problem to a nearest‐neighbour problem in a low‐dimensional feature space, and follow this with a cascade of tests for geometric clustering of potential matches. Our algorithm robustly handles noisy real‐world scanner data, obtaining a recognition performance comparable to that of state‐of‐the‐art methods. In practice, it scales linearly with scene size and achieves a high absolute throughput, processing half a terabyte of scanner data overnight on a dual socket commodity PC.

Abstract In this paper, we propose a new paradigm for free‐form shape deformation. Standard deformable models minimize an energy measuring the distance to a single target shape. We propose a new, “mutable” elastic model. It represents complex geometry by a collection of parts and measures the distance of each part measures to a larger set of alternative rest configurations. By detecting and reacting to local switches between best‐matching rest states, we build a 3D sculpting system: It takes a structured shape consisting of parts and replacement rules as input. The shape can subsequently be elongated, compressed, bent, cut, and merged within a constraints‐based free‐form editing interface, where alternative rest‐states model to such changes. In practical experiments, we show that the approach yields a surprisingly intuitive and easy to implement interface for interactively designing objects described by such discrete shape grammars, for which direct shape control mechanisms were typically lacking.

Abstract This work addresses the challenge of intuitive appearance editing in scenes with complex geometric layout and complex, spatially‐varying indirect lighting. In contrast to previous work, that aimed to edit surface reflectance, our system allows a user to freely manipulate the surface light field. It then finds the best surface reflectance that “explains” the surface light field manipulation. Instead of classic L2fitting of reflectance to a combination of incoming and exitant illumination, our system infers a sparse L0change of shading parameters instead. Consequently, our system does not require “diffuse” or “glossiness” brushes or any such understanding of the underlying reflectance parametrization. Instead, it infers reflectance changes from scribbles made by a single simple color brush tool alone: Drawing a highlight will increase Phong specular; blurring a mirror reflection will decrease glossiness; etc. A sparse‐solver framework operating on a novel point‐based, pre‐convolved lighting representation in combination with screen‐space edit upsampling allows to perform editing interactively on a GPU.

Abstract This paper addresses the problem of detecting objects in 3D scans according to object classes learned from sparse user annotation. We model objects belonging to a class by a set of fully correlated parts, encoding dependencies between local shapes of different parts as well as their relative spatial arrangement. For an efficient and comprehensive retrieval of instances belonging to a class of interest, we introduce a new approximate inference scheme and a corresponding planning procedure. We extend our technique to hierarchical composite structures, reducing training effort and modeling spatial relations between detected instances. We evaluate our method on a number of real‐world 3D scans and demonstrate its benefits as well as the performance of the new inference algorithm.

Capturing the skeleton motion and detailed time-varying surface geometry of multiple, closely interacting peoples is a very challenging task, even in a multicamera setup, due to frequent occlusions and ambiguities in feature-to-person assignments. To address this task, we propose a framework that exploits multiview image segmentation. To this end, a probabilistic shape and appearance model is employed to segment the input images and to assign each pixel uniquely to one person. Given the articulated template models of each person and the labeled pixels, a combined optimization scheme, which splits the skeleton pose optimization problem into a local one and a lower dimensional global one, is applied one by one to each individual, followed with surface estimation to capture detailed nonrigid deformations. We show on various sequences that our approach can capture the 3D motion of humans accurately even if they move rapidly, if they wear wide apparel, and if they are engaged in challenging multiperson motions, including dancing, wrestling, and hugging.

Traditionally, computer graphics has been concerned with producing imagery that is as physically accurate as possible. But accurate physical simulation of geometry, lighting, and material properties of a visual scene can be cumbersome and time consuming. At the same time, human vision is far from accurate, which offers an enormous opportunity to create imagery at a reduced computational cost as well as with less reliance on human modelers. As a result, a recent trend is toward accepting perceptual plausibility instead of physical accuracy as a guiding principle in the design of modeling and rendering systems. This requires us to understand visual realism, which involves both learning statistical regularities of the world, for instance, by employing huge amounts of data, as well as human's visual perception of it. This paper addresses issues related to understanding realism, presents several applications, and discusses what this interesting approach may lead to in the future.

We propose a non-permanent add-on that enables plenoptic imaging with standard cameras. Our design is based on a physical copying mechanism that multiplies a sensor image into a number of identical copies that still carry the plenoptic information of interest. Via different optical filters, we can then recover the desired information. A minor modification of the design also allows for aperture sub-sampling and, hence, light-field imaging. As the filters in our design are exchangeable, a reconfiguration for different imaging purposes is possible. We show in a prototype setup that high dynamic range, multispectral, polarization, and light-field imaging can be achieved with our design.

We propose an approach to "pack" a set of two-dimensional graphical primitives into a spatial layout that follows artistic goals. We formalize this process as projecting from a high-dimensional feature space into a 2D layout. Our system does not expose the control of this projection to the user in form of sliders or similar interfaces. Instead, we infer the desired layout of all primitives from interactive placement of a small subset of example primitives. To produce a pleasant distribution of primitives with spatial extend, we propose a novel generalization of Centroidal Voronoi Tesselation which equalizes the distances between boundaries of nearby primitives. Compared to previous primitive distribution approaches our GPU implementation achieves both better fidelity and asymptotically higher speed. A user study evaluates the system's usability.

Many efficient computational methods for physical simulation are based on model reduction. We propose new model reduction techniques for the approximation of reduced forces and for the construction of reduced shape spaces of deformable objects that accelerate the construction of a reduced dynamical system, increase the accuracy of the approximation, and simplify the implementation of model reduction. Based on the techniques, we introduce schemes for real-time simulation of deformable objects and interactive deformation-based editing of triangle or tet meshes. We demonstrate the effectiveness of the new techniques in different experiments with elastic solids and shells and compare them to alternative approaches.

Visualization techniques often use color to present categorical differences to a user. When selecting a color palette, the perceptual qualities of color need careful consideration. Large coherent groups visually suppress smaller groups and are often visually dominant in images. This paper introduces the concept of class visibility used to quantitatively measure the utility of a color palette to present coherent categorical structure to the user. We present a color optimization algorithm based on our class visibility metric to make categorical differences clearly visible to the user. We performed two user experiments on user preference and visual search to validate our visibility measure over a range of color palettes. The results indicate that visibility is a robust measure, and our color optimization can increase the effectiveness of categorical data visualizations.

We present a new spatio-temporal method for markerless motion capture. We reconstruct the pose and motion of a character from a multi-view video sequence without requiring the cameras to be synchronized and without aligning captured frames in time. By formulating the model-to-image similarity measure as a temporally continuous functional, we are also able to reconstruct motion in much higher temporal detail than was possible with previous synchronized approaches. By purposefully running cameras unsynchronized we can capture even very fast motion at speeds that off-the-shelf but high quality cameras provide.

Abstract Rigging an arbitrary 3D character by creating an animation skeleton is a time‐consuming process even for experienced animators. In this paper, we present an algorithm that automatically creates animation rigs for multi‐component 3D models, as they are typically found in online shape databases. Our algorithm takes as input a multi‐component model and an input animation skeleton with associated motion data. It then creates a target skeleton for the input model, calculates the rigid skinning weights, and a mapping between the joints of the target skeleton and the input animation skeleton. The automatic approach does not need additional semantic information, such as component labels or user‐provided correspondences, and succeeds on a wide range of models where the number of components is significantly different. It implicitly handles large scale and proportional differences between input and target skeletons and can deal with certain morphological differences, e.g., if input and target have different numbers of limbs. The output of our algorithm can be directly used in a retargeting system to create a plausible animated character.

Abstract Extremal lines and surfaces are features of a 3D scalar field where the scalar function becomes minimal or maximal with respect to a local neighborhood . These features are important in many applications, e.g. computer tomography, fluid dynamics, cell biology . We present a novel topological method to extract these features using discrete Morse theory. In particular, we extend the notion of ‘separatrix persistence’ from 2D to 3D, which gives us a robust estimation of the feature strength for extremal lines and surfaces. Not only does it allow us to determine the most important (parts of) extremal lines and surfaces, it also serves as a robust filtering measure of noise‐induced structures. Our purely combinatorial method does not require derivatives or any other numerical computations .

Abstract Synthetically generating images and video frames of complex 3D scenes using some photo‐realistic rendering software is often prone to artifacts and requires expert knowledge to tune the parameters. The manual work required for detecting and preventing artifacts can be automated through objective quality evaluation of synthetic images. Most practical objective quality assessment methods of natural images rely on a ground‐truth reference, which is often not available in rendering applications. While general purpose no‐reference image quality assessment is a difficult problem, we show in a subjective study that the performance of a dedicated no‐reference metric as presented in this paper can match the state‐of‐the‐art metrics that do require a reference. This level of predictive power is achieved exploiting information about the underlying synthetic scene (e.g., 3D surfaces, textures) instead of merely considering color, and training our learning framework with typical rendering artifacts. We show that our method successfully detects various non‐trivial types of artifacts such as noise and clamping bias due to insufficient virtual point light sources, and shadow map discretization artifacts. We also briefly discuss an inpainting method for automatic correction of detected artifacts.

Abstract We present a system that allows new shapes to be created by blending between shapes taken from a database. We treat the shape as a composition of parts; blending is performed by recombining parts from different shapes according to constraints deduced by shape analysis. The analysis involves shape segmentation, contact analysis, and symmetry detection. The system can be used to rapidly instantiate new models that have similar symmetry and adjacency structure to the database shapes, yet vary in appearance.

Abstract In this paper, we develop a theoretical framework for characterizing shapes by building blocks. We address two questions: First, how do shape correspondences induce building blocks? For this, we introduce a new representation for structuring partial symmetries (partial self‐correspondences), which we call “microtiles”. Starting from input correspondences that form point‐wise equivalence relations, microtiles are obtained by grouping connected components of points that share the same set of symmetry transformations. The decomposition is unique, requires no parameters beyond the input correspondences, and encodes the partial symmetries of all subsets of the input. The second question is: What is the class of shapes that can be assembled from these building blocks? Here, we specifically consider r‐similarity as correspondence model, i.e., matching of local r‐neighborhoods. Our main result is that the microtiles of the partial r‐symmetries of an object S can build all objects that are (r+ε)‐similar to S for any ε >0. Again, the construction is unique. Furthermore, we give necessary conditions for a set of assembly rules for the pairwise connection of tiles. We describe a practical algorithm for computing microtile decompositions under rigid motions, a corresponding prototype implementation, and conduct a number of experiments to visualize the structural properties in practice.

Abstract In this paper, we present an overview of the achievements accomplished to date in the field of computer‐aided relief generation. We delineate the problem, classify different solutions, analyse similarities, investigate developments and review the approaches according to their particular relative strengths and weaknesses. Moreover, we describe remaining challenges and point out prospective extensions. In consequence, this survey is addressed to both researchers and artists, through providing valuable insights into the theory behind the different concepts in this field and augmenting the options available among the methods presented with regard to practical application.

Abstract This work proposes a technique to transfer the material style or mood from a guide source such as an image or video onto a target 3D scene. It formulates the problem as a combinatorial optimization of assigning discrete materials extracted from the guide source to discrete objects in the target 3D scene. The assignment is optimized to fulfill multiple goals: overall image mood based on several image statistics; spatial material organization and grouping as well as geometric similarity between objects that were assigned to similar materials. To be able to use common uncalibrated images and videos with unknown geometry and lighting as guides, a material estimation derives perceptually plausible reflectance, specularity, glossiness, and texture. Finally, results produced by our method are compared to manual material assignments in a perceptual study.

Abstract Size matters. Human perception most naturally relates relative extent, area or volume to importance, nearness and weight. Reversely, conveying importance of something by depicting it at a different size is a classic artistic principle, in particular when importance varies across a domain. One striking example is the neuronal homunculus; a human figure where the size of each body part is proportional to the neural density on that part. In this work we propose an approach which changes local size of a 2D image or 3D surface and, at the same time, minimizes distortion, prevails smoothness, and, most importantly, avoids fold‐overs (collisions). We employ a parallel, two‐stage optimization process, that scales the shape non‐uniformly according to an interactively‐defined importance map and then solves for a nearby, self‐intersection‐free configuration. The results include an interactive 3D‐rendered version of the classic sensorical homunculus but also a range of images and surfaces with different importance maps.

Abstract Sophisticated video processing effects require both image and geometry information. We explore the possibility to augment a video camera with a recent infrared time‐of‐flight depth camera, to capture high‐resolution RGB and low‐resolution, noisy depth at video frame rates. To turn such a setup into a practical RGBZ video camera, we develop efficient data filtering techniques that are tailored to the noise characteristics of IR depth cameras. We first remove typical artefacts in the RGBZ data and then apply an efficient spatiotemporal denoising and upsampling scheme. This allows us to record temporally coherent RGBZ videos at interactive frame rates and to use them to render a variety of effects in unprecedented quality. We show effects such as video relighting, geometry‐based abstraction and stylisation, background segmentation and rendering in stereoscopic 3D.

Abstract The incident indirect light over a range of image pixels is often coherent. Two common approaches to exploit this inter‐pixel coherence to improve rendering performance are Irradiance Caching and Radiance Caching. Both compute incident indirect light only for a small subset of pixels (the cache), and later interpolate between pixels. Irradiance Caching uses scalar values that can be interpolated efficiently, but cannot account for shading variations caused by normal and reflectance variation between cache items. Radiance Caching maintains directional information, e.g., to allow highlights between cache items, but at the cost of storing and evaluating a Spherical Harmonics (SH) function per pixel. The arithmetic and bandwidth cost for this evaluation is linear in the number of coefficients and can be substantial. In this paper, we propose a method to replace it by an efficient per‐cache item pre‐filtering based on MIP maps — such as previously done for environment maps — leading to a single constant‐time lookup per pixel. Additionally, per‐cache item geometry statistics stored in distance‐MIP maps are used to improve the quality of each pixel's lookup. Our approximate interactive global illumination approach is an order of magnitude faster than Radiance Caching with Phong BRDFs and can be combined with Monte Carlo‐raytracing, Point‐based Global Illumination or Instant Radiosity.

We present an approach to high-level shape editing that adapts the structure of the shape while maintaining its global characteristics. Our main contribution is a new algebraic model of shape structure that characterizes shapes in terms of linked translational patterns. The space of shapes that conform to this characterization is parameterized by a small set of numerical parameters bounded by a set of linear constraints. This convex space permits a direct exploration of variations of the input shape. We use this representation to develop a robust interactive system that allows shapes to be intuitively manipulated through sparse constraints.

Reliable detection of global illumination and rendering artifacts in the form of localized distortion maps is important for many graphics applications. Although many quality metrics have been developed for this task, they are often tuned for compression/transmission artifacts and have not been evaluated in the context of synthetic CG-images. In this work, we run two experiments where observers use a brush-painting interface to directly mark image regions with noticeable/objectionable distortions in the presence/absence of a high-quality reference image, respectively. The collected data shows a relatively high correlation between the with-reference and no-reference observer markings. Also, our demanding per-pixel image-quality datasets reveal weaknesses of both simple (PSNR, MSE, sCIE-Lab) and advanced (SSIM, MS-SSIM, HDR-VDP-2) quality metrics. The most problematic are excessive sensitivity to brightness and contrast changes, the calibration for near visibility-threshold distortions, lack of discrimination between plausible/implausible illumination, and poor spatial localization of distortions for multi-scale metrics. We believe that our datasets have further potential in improving existing quality metrics, but also in analyzing the saliency of rendering distortions, and investigating visual equivalence given our with- and no-reference data.

Binocular disparity is one of the most important depth cues used by the human visual system. Recently developed stereo-perception models allow us to successfully manipulate disparity in order to improve viewing comfort, depth discrimination as well as stereo content compression and display. Nonetheless, all existing models neglect the substantial influence of luminance on stereo perception. Our work is the first to account for the interplay of luminance contrast (magnitude/frequency) and disparity and our model predicts the human response to complex stereo-luminance images. Besides improving existing disparity-model applications (e.g., difference metrics or compression), our approach offers new possibilities, such as joint luminance contrast and disparity manipulation or the optimization of auto-stereoscopic content. We validate our results in a user study, which also reveals the advantage of considering luminance contrast and its significant impact on disparity manipulation techniques.

The material found on 3D objects and their parts in our everyday surroundings is highly correlated with the geometric shape of the parts and their relation to other parts of the same object. This work proposes to model this context-dependent correlation by learning it from a database containing several hundreds of objects and their materials. Given a part-based 3D object without materials, the learned model can be used to fully automatically assign plausible material parameters, including diffuse color, specularity, gloss, and transparency. Further, we propose a user interface that provides material suggestions. This user-interface can be used, for example, to refine the automatic suggestion. Once a refinement has been made, the model incorporates this information, and the automatic assignment is incrementally improved. Results are given for objects with different numbers of parts and with different topological complexity. A user study validates that our method significantly simplifies and accelerates the material assignment task compared to other approaches.

Human stereo perception of glossy materials is substantially different from the perception of diffuse surfaces: A single point on a diffuse object appears the same for both eyes, whereas it appears different to both eyes on a specular object. As highlights are blurry reflections of light sources they have depth themselves, which is different from the depth of the reflecting surface. We call this difference in depth impression the "highlight disparity". Due to artistic motivation, for technical reasons, or because of incomplete data, highlights often have to be depicted on-surface, without any disparity. However, it has been shown that a lack of disparity decreases the perceived glossiness and authenticity of a material. To remedy this contradiction, our work introduces a technique for depiction of glossy materials, which improves over simple on-surface highlights, and avoids the problems of physical highlights. Our technique is computationally simple, can be easily integrated in an existing (GPU) shading system, and allows for local and interactive artistic control.

In this article, we consider the problem of animation reconstruction, that is, the reconstruction of shape and motion of a deformable object from dynamic 3D scanner data, without using user-provided template models. Unlike previous work that addressed this problem, we do not rely on locally convergent optimization but present a system that can handle fast motion, temporally disrupted input, and can correctly match objects that disappear for extended time periods in acquisition holes due to occlusion. Our approach is motivated by cartography: We first estimate a few landmark correspondences, which are extended to a dense matching and then used to reconstruct geometry and motion. We propose a number of algorithmic building blocks: a scheme for tracking landmarks in temporally coherent and incoherent data, an algorithm for robust estimation of dense correspondences under topological noise, and the integration of local matching techniques to refine the result. We describe and evaluate the individual components and propose a complete animation reconstruction pipeline based on these ideas. We evaluate our method on a number of standard benchmark datasets and show that we can obtain correct reconstructions in situations where other techniques fail completely or require additional user guidance such as a template model.

Recent progress in passive facial performance capture has shown impressively detailed results on highly articulated motion. However, most methods rely on complex multi-camera set-ups, controlled lighting or fiducial markers. This prevents them from being used in general environments, outdoor scenes, during live action on a film set, or by freelance animators and everyday users who want to capture their digital selves. In this paper, we therefore propose a lightweight passive facial performance capture approach that is able to reconstruct high-quality dynamic facial geometry from only a single pair of stereo cameras. Our method succeeds under uncontrolled and time-varying lighting, and also in outdoor scenes. Our approach builds upon and extends recent image-based scene flow computation, lighting estimation and shading-based refinement algorithms. It integrates them into a pipeline that is specifically tailored towards facial performance reconstruction from challenging binocular footage under uncontrolled lighting. In an experimental evaluation, the strong capabilities of our method become explicit: We achieve detailed and spatio-temporally coherent results for expressive facial motion in both indoor and outdoor scenes -- even from low quality input images recorded with a hand-held consumer stereo camera. We believe that our approach is the first to capture facial performances of such high quality from a single stereo rig and we demonstrate that it brings facial performance capture out of the studio, into the wild, and within the reach of everybody.

Height fields have become an important element of realistic real-time image synthesis to represent surface details. In this paper, we focus on the frequent case of static height-field data, for which we can precompute acceleration structures. While many rendering algorithms exist that impose tradeoffs between speed and accuracy, we show that even accurate rendering can be combined with high performance. A careful analysis of the surface defined by the height values, leads to an efficient and accurate precomputation method. As a result, each texel stores a safety shape inside which a ray cannot cross the surface twice. This property ensures that no intersections are missed during the efficient marching method. Our analysis is general and can even consider visibility constraints that are robustly integrated into the precomputation. Further, we propose a particular instance of safety shapes with little memory overhead, which results in a rendering algorithm that outperforms existing methods, both in terms of accuracy and performance.

We present a system for the annotation and augmentation of mountain photographs. The key issue resides in the registration of a given photograph with a 3D geo-referenced terrain model. Typical outdoor images contain little structural information, particularly mountain scenes whose aspect changes drastically across seasons and varying weather conditions. Existing approaches usually fail on such difficult scenarios. To avoid the burden of manual registration, we propose a novel automatic technique. Given only a viewpoint and FOV estimates, the technique is able to automatically derive the pose of the camera relative to the geometric terrain model. We make use of silhouette edges, which are among most reliable features that can be detected in the targeted situations. Using an edge detection algorithm, our technique then searches for the best match with silhouette edges rendered using the synthetic model. We develop a robust matching metric allowing us to cope with the inevitable noise affecting detected edges (e.g. due to clouds, snow, rocks, forests, or any phenomenon not encoded in the digital model). Once registered against the model, photographs can easily be augmented with annotations (e.g. topographic data, peak names, paths), which would otherwise imply a tedious fusion process. We further illustrate various other applications, such as 3D model-assisted image enhancement, or, inversely, texturing of digital models.

Loopy belief propagation (LBP) is a powerful tool for approximate inference in Markov random fields (MRFs). However, for problems with large state spaces, the runtime costs are often prohibitively high. In this paper, we present a new LBP algorithm that represents all beliefs, marginals, and messages in a wavelet representation, which can encode the probabilistic information much more compactly. Unlike previous work, our algorithm operates solely in the wavelet domain. This yields an output-sensitive algorithm where the running time depends mostly on the information content rather than the discretization resolution. We apply the new technique to typical problems with large state spaces such as image matching and wide-baseline optical flow where we observe a significantly improved scaling behavior with discretization resolution. For large problems, the new technique is significantly faster than even an optimized spatial domain implementation.

We present a markerless motion capture approach that reconstructs the skeletal motion and detailed time-varying surface geometry of two closely interacting people from multi-view video. Due to ambiguities in feature-to-person assignments and frequent occlusions, it is not feasible to directly apply single-person capture approaches to the multi-person case. We therefore propose a combined image segmentation and tracking approach to overcome these difficulties. A new probabilistic shape and appearance model is employed to segment the input images and to assign each pixel uniquely to one person. Thereafter, a single-person markerless motion and surface capture approach can be applied to each individual, either one-by-one or in parallel, even under strong occlusions. We demonstrate the performance of our approach on several challenging multi-person motions, including dance and martial arts, and also provide a reference dataset for multi-person motion capture with ground truth.

We introduce three-dimensional kaleidoscopic imaging, a promising alternative for recording multi-view imagery. The main limitation of multi-view reconstruction techniques is the limited number of views that are available from multi-camera systems, especially for dynamic scenes. Our new system is based on imaging an object inside a kaleidoscopic mirror system. We show that this approach can generate a large number of high-quality views well distributed over the hemisphere surrounding the object in a single shot. In comparison to existing multi-view systems, our method offers a number of advantages: it is possible to operate with a single camera, the individual views are perfectly synchronized, and they have the same radiometric and colorimetric properties. We describe the setup both theoretically, and provide methods for a practical implementation. Enabling interfacing to standard multi-view algorithms for further processing is an important goal of our techniques.

In recent years, depth cameras have become a widely available sensor type that captures depth images at real-time frame rates. Even though recent approaches have shown that 3D pose estimation from monocular 2.5D depth images has become feasible, there are still challenging problems due to strong noise in the depth data and self-occlusions in the motions being captured. In this paper, we present an efficient and robust pose estimation framework for tracking full-body motions from a single depth image stream. Following a data-driven hybrid strategy that combines local optimization with global retrieval techniques, we contribute several technical improvements that lead to speed-ups of an order of magnitude compared to previous approaches. In particular, we introduce a variant of Dijkstra's algorithm to efficiently extract pose features from the depth data and describe a novel late-fusion scheme based on an efficiently computable sparse Hausdorff distance to combine local and global pose estimates. Our experiments show that the combination of these techniques facilitates real-time tracking with stable results even for fast and complex motions, making it applicable to a wide range of inter-active scenarios.

Human motion capturing (HMC) from multiview image sequences is an extremely difficult problem due to depth and orientation ambiguities and the high dimensionality of the state space. In this paper, we introduce a novel hybrid HMC system that combines video input with sparse inertial sensor input. Employing an annealing particle-based optimization scheme, our idea is to use orientation cues derived from the inertial input to sample particles from the manifold of valid poses. Then, visual cues derived from the video input are used to weight these particles and to iteratively derive the final pose. As our main contribution, we propose an efficient sampling procedure where the particles are derived analytically using inverse kinematics on the orientation cues. Additionally, we introduce a novel sensor noise model to account for uncertainties based on the von Mises-Fisher distribution. Doing so, orientation constraints are naturally fulfilled and the number of needed particles can be kept very small. More generally, our method can be used to sample poses that fulfill arbitrary orientation or positional kinematic constraints. In the experiments, we show that our system can track even highly dynamic motions in an outdoor environment with changing illumination, background clutter, and shadows.

We present an approach for modeling the human body by Sums of spatial Gaussians (SoG), allowing us to perform fast and high-quality markerless motion capture from multi-view video sequences. The SoG model is equipped with a color model to represent the shape and appearance of the human and can be reconstructed from a sparse set of images. Similar to the human body, we also represent the image domain as SoG that models color consistent image blobs. Based on the SoG models of the image and the human body, we introduce a novel continuous and differentiable model-to-image similarity measure that can be used to estimate the skeletal motion of a human at 5-15 frames per second even for many camera views. In our experiments, we show that our method, which does not rely on silhouettes or training data, offers an good balance between accuracy and computational cost.

We present an approach to add true fine-scale spatio-temporal shape detail to dynamic scene geometry captured from multi-view video footage. Our approach exploits shading information to recover the millimeter-scale surface structure, but in contrast to related approaches succeeds under general unconstrained lighting conditions. Our method starts off from a set of multi-view video frames and an initial series of reconstructed coarse 3D meshes that lack any surface detail. In a spatio-temporal maximum a posteriori probability (MAP) inference framework, our approach first estimates the incident illumination and the spatially-varying albedo map on the mesh surface for every time instant. Thereafter, albedo and illumination are used to estimate the true geometric detail visible in the images and add it to the coarse reconstructions. The MAP framework uses weak temporal priors on lighting, albedo and geometry which improve reconstruction quality yet allow for temporal variations in the data.

We present a time skewing algorithm that breaks the memory wall for certain iterative stencil computations. A stencil computation, even with constant weights, is a completely memory-bound algorithm. For example, for a large 3D domain of 5003doubles and 100 iterations on a quad-core Xeon X5482 3.2GHz system, a hand-vectorized and parallelized naive 7-point stencil implementation achieves only 1.4 GFLOPS because the system memory bandwidth limits the performance. Although many efforts have been undertaken to improve the performance of such nested loops, for large data sets they still lag far behind synthetic benchmark performance. The state-of-art automatic locality optimizer PluTo achieves 3.7 GFLOPS for the above stencil, whereas a parallel benchmark executing the inner stencil computation directly on registers performs at 25.1 GFLOPS. In comparison, our algorithm achieves 13.0 GFLOPS (52% of the stencil peak benchmark).We present results for 2D and 3D domains in double precision including problems with gigabyte large data sets. The results are compared against hand-optimized naive schemes, PluTo, the stencil peak benchmark and results from literature. For constant stencils of slope one we break the dependence on the low system bandwidth and achieve at least 50% of the stencil peak, thus performing within a factor two of an ideal system with infinite bandwidth (the benchmark runs on registers without memory access). For large stencils and banded matrices the additional data transfers let the limitations of the system bandwidth come into play again, however, our algorithm still gains a large improvement over the other schemes.

Abstract We address the problem of partial symmetry detection, i.e., the identification of building blocks a complex shape is composed of. Previous techniques identify parts that relate to each other by simple rigid mappings, similarity transforms, or, more recently, intrinsic isometries. Our approach generalizes the notion of partial symmetries to more general deformations. We introduce subspace symmetries whereby we characterize similarity by requiring the set of symmetric parts to form a low dimensional shape space. We present an algorithm to discover subspace symmetries based on detecting linearly correlated correspondences among graphs of invariant features. We evaluate our technique on various data sets. We show that for models with pronounced surface features, subspace symmetries can be found fully automatically. For complicated cases, a small amount of user input is used to resolve ambiguities. Our technique computes dense correspondences that can subsequently be used in various applications, such as model repair and denoising.

Abstract This paper deals with the challenge of physically displaying reflectance, i.e., the appearance of a surface and its variation with the observer position and the illuminating environment. This is commonly described by the bidirectional reflectance distribution function (BRDF). We provide a catalogue of criteria for the display of BRDFs, and sketch a few orthogonal approaches to solving the problem in an optically passive way. Our specific implementation is based on a liquid surface, on which we excite waves in order to achieve a varying degree of anisotropic roughness. The resulting probability density function of the surface normal is shown to follow a Gaussian distribution similar to most established BRDF models.

Abstract In this paper, we focus on efficient compression and streaming of frames rendered from a dynamic 3D model. Remote rendering and on‐the‐fly streaming become increasingly attractive for interactive applications. Data is kept confidential and only images are sent to the client. Even if the client's hardware resources are modest, the user can interact with state‐of‐the‐art rendering applications executed on the server. Our solution focuses on augmented video information, e.g., by depth, which is key to increase robustness with respect to data loss, image reconstruction, and is an important feature for stereo vision and other client‐side applications. Two major challenges arise in such a setup. First, the server workload has to be controlled to support many clients, second the data transfer needs to be efficient. Consequently, our contributions are twofold. First, we reduce the server‐based computations by making use of sparse sampling and temporal consistency to avoid expensive pixel evaluations. Second, our data‐transfer solution takes limited bandwidths into account, is robust to information loss, and compression and decompression are efficient enough to support real‐time interaction. Our key insight is to tailor our method explicitly for rendered 3D content and shift some computations on client GPUs, to better balance the server/client workload. Our framework is progressive, scalable, and allows us to stream augmented high‐resolution (e.g., HD‐ready) frames with small bandwidth on standard hardware.

Abstract We propose an algorithm to compute interactive indirect illumination in dynamic scenes containing millions of triangles. It makes use of virtual point lights (VPL) to compute bounced illumination and a point‐based scene representation to query indirect visibility, similar to Imperfect Shadow Maps (ISM). To ensure a high fidelity of indirect light and shadows, our solution is made view‐adaptive by means of two orthogonal improvements: First, the VPL distribution is chosen to provide more detail, that is, more dense VPL sampling, where these contribute most to the current view. Second, the scene representation for indirect visibility is adapted to ensure geometric detail where it affects indirect shadows in the current view.

Abstract Finding the best makeup for a given human face is an art in its own right. Experienced makeup artists train for years to be skilled enough to propose a best‐fit makeup for an individual. In this work we propose a system that automates this task. We acquired the appearance of 56 human faces, both without and with professional makeup. To this end, we use a controlled‐light setup, which allows to capture detailed facial appearance information, such as diffuse reflectance, normals, subsurface‐scattering, specularity, or glossiness. A 3D morphable face model is used to obtain 3D positional information and to register all faces into a common parameterization. We then define makeup to be the change of facial appearance and use the acquired database to find a mapping from the space of human facial appearance to makeup. Our main application is to use this mapping to suggest the best‐fit makeup for novel faces that are not in the database. Further applications are makeup transfer, automatic rating of makeup, makeup‐training, or makeup‐exaggeration. As our makeup representation captures a change in reflectance and scattering, it allows us to synthesize faces with makeup in novel 3D views and novel lighting with high realism. The effectiveness of our approach is further validated in a user‐study.

Abstract Feature detection in geometric datasets is a fundamental tool for solving shape matching problems such as partial symmetry detection. Traditional techniques usually employ a priori models such as crease lines that are unspecific to the actual application. Our paper examines the idea of learning geometric features. We introduce a formal model for a class of linear feature constellations based on a Markov chain model and propose a novel, efficient algorithm for detecting a large number of features simultaneously. After a short user‐guided training stage, in which one or a few example lines are sketched directly onto the input data, our algorithm automatically finds all pieces of geometry similar to the marked areas. In particular, the algorithm is able recognize larger classes of semantically similar but geometrically varying features, which is very difficult using unsupervised techniques. In a number of experiments, we apply our technique to point cloud data from 3D scanners. The algorithm is able to detect features with very low rates of false positives and negatives and to recognize broader classes of similar geometry (such as “windows” in a building scan) even from few training examples, thereby significantly improving over previous unsupervised techniques.

Abstract Recently, the problem of intrinsic shape matching has received a lot of attention. A number of algorithms have been proposed, among which random‐sampling‐based techniques have been particularly successful due to their generality and efficiency. We introduce a new sampling‐based shape matching algorithm that uses a planning step to find optimized “landmark” points. These points are matched first in order to maximize the information gained and thus minimize the sampling costs. Our approach makes three main contributions: First, the new technique leads to a significant improvement in performance, which we demonstrate on a number of benchmark scenarios. Second, our technique does not require any keypoint detection. This is often a significant limitation for models that do not show sufficient surface features. Third, we examine the actual numerical degrees of freedom of the matching problem for a given piece of geometry. In contrast to previous results, our estimates take into account unprecise geodesics and potentially numerically unfavorable geometry of general topology, giving a more realistic complexity estimate.

This paper introduces a new structure-aware shape deformation technique. The key idea is to detect continuous and discrete regular patterns and ensure that these patterns are preserved during free-form deformation. We propose a variational deformation model that preserves these structures, and a discrete algorithm that adaptively inserts or removes repeated elements in regular patterns to minimize distortion. As a tool for such structural adaptation, we introduce sliding dockers, which represent repeatable elements that fit together seamlessly for arbitrary repetition counts. We demonstrate the presented approach on a number of complex 3D models from commercial shape libraries.

Binocular disparity is an important cue for the human visual system to recognize spatial layout, both in reality and simulated virtual worlds. This paper introduces a perceptual model of disparity for computer graphics that is used to define a metric to compare a stereo image to an alternative stereo image and to estimate the magnitude of the perceived disparity change. Our model can be used to assess the effect of disparity to control the level of undesirable distortions or enhancements (introduced on purpose). A number of psycho-visual experiments are conducted to quantify the mutual effect of disparity magnitude and frequency to derive the model. Besides difference prediction, other applications include compression, and re-targeting. We also present novel applications in form of hybrid stereo images and backward-compatible stereo. The latter minimizes disparity in order to convey a stereo impression if special equipment is used but produces images that appear almost ordinary to the naked eye. The validity of our model and difference metric is again confirmed in a study.

Lens flare is caused by light passing through a photographic lens system in an unintended way. Often considered a degrading artifact, it has become a crucial component for realistic imagery and an artistic means that can even lead to an increased perceived brightness. So far, only costly offline processes allowed for convincing simulations of the complex light interactions. In this paper, we present a novel method to interactively compute physically-plausible flare renderings for photographic lenses. The underlying model covers many components that are important for realism, such as imperfections, chromatic and geometric lens aberrations, and antireflective lens coatings. Various acceleration strategies allow for a performance/quality tradeoff, making our technique applicable both in real-time applications and in high-quality production rendering. We further outline artistic extensions to our system.

The development of methods and tools for the generation of visually appealing motion sequences using prerecorded motion capture data has become an important research area in computer animation. In particular, data-driven approaches have been used for reconstructing high-dimensional motion sequences from low-dimensional control signals. In this article, we contribute to this strand of research by introducing a novel framework for generating full-body animations controlled by only four 3D accelerometers that are attached to the extremities of a human actor. Our approach relies on a knowledge base that consists of a large number of motion clips obtained from marker-based motion capturing. Based on the sparse accelerometer input a cross-domain retrieval procedure is applied to build up a lazy neighborhood graph in an online fashion. This graph structure points to suitable motion fragments in the knowledge base, which are then used in the reconstruction step. Supported by a kd-tree index structure, our procedure scales to even large datasets consisting of millions of frames. Our combined approach allows for reconstructing visually plausible continuous motion streams, even in the presence of moderate tempo variations which may not be directly reflected by the given knowledge base.

We present a method to synthesize plausible video sequences of humans according to user-defined body motions and viewpoints. We first capture a small database of multi-view video sequences of an actor performing various basic motions. This database needs to be captured only once and serves as the input to our synthesis algorithm. We then apply a marker-less model-based performance capture approach to the entire database to obtain pose and geometry of the actor in each database frame. To create novel video sequences of the actor from the database, a user animates a 3D human skeleton with novel motion and viewpoints. Our technique then synthesizes a realistic video sequence of the actor performing the specified motion based only on the initial database. The first key component of our approach is a new efficient retrieval strategy to find appropriate spatio-temporally coherent database frames from which to synthesize target video frames. The second key component is a warping-based texture synthesis approach that uses the retrieved most-similar database frames to synthesize spatio-temporally coherent target video frames. For instance, this enables us to easily create video sequences of actors performing dangerous stunts without them being placed in harm's way. We show through a variety of result videos and a user study that we can synthesize realistic videos of people, even if the target motions and camera views are different from the database content.

Given a multi-exposure sequence of a scene, our aim is to recover the absolute irradiance falling onto a linear camera sensor. The established approach is to perform a weighted average of the scaled input exposures. However, there is no clear consensus on the appropriate weighting to use. We propose a weighting function that produces statistically optimal estimates under the assumption of compound-Gaussian noise. Our weighting is based on a calibrated camera model that accounts for all noise sources. This model also allows us to simultaneously estimate the irradiance and its uncertainty. We evaluate our method on simulated and real world photographs, and show that we consistently improve the signal-to-noise ratio over previous approaches. Finally, we show the effectiveness of our model for optimal exposure sequence selection and HDR image denoising.

In this paper we propose a multilinear model of human pose and body shape which is estimated from a database of registered 3D body scans in different poses. The model is generated by factorizing the measurements into pose and shape dependent components. By combining it with an ICP based registration method, we are able to estimate pose and body shape of dressed subjects from single images. If several images of the subject are available, shape and poses can be optimized simultaneously for all input images. Additionally, while estimating pose and shape, we use the model as a virtual calibration pattern and also recover the parameters of the perspective camera model the images were created with.

Given a set of 2D images, we propose a novel approach for the reconstruction of straight 3D line segments that represent the underlying geometry of static 3D objects in the scene. Such an algorithm is especially useful for the automatic 3D reconstruction of man-made environments. The main contribution of our approach is the generation of an improved reconstruction by imposing global topological constraints given by connections between neighbouring lines. Additionally, our approach does not employ explicit line matching between views, thus making it more robust against image noise and partial occlusion. Furthermore, we suggest a technique to merge independent reconstructions, that are generated from different base images, which also helps to remove outliers. The proposed algorithm is evaluated on synthetic and real scenes by comparison with ground truth.

In this work, we present an approach to fuse video with orientation data obtained from extended inertial sensors to improve and stabilize full-body human motion capture. Even though video data is a strong cue for motion analysis, tracking artifacts occur frequently due to ambiguities in the images, rapid motions, occlusions or noise. As a complementary data source, inertial sensors allow for drift-free estimation of limb orientations even under fast motions. However, accurate position information cannot be obtained in continuous operation. Therefore, we propose a hybrid tracker that combines video with a small number of inertial units to compensate for the drawbacks of each sensor type: on the one hand, we obtain drift-free and accurate position information from video data and, on the other hand, we obtain accurate limb orientations and good performance under fast motions from inertial sensors. In several experiments we demonstrate the increased performance and stability of our human motion tracker.

This paper presents a real-time face recognition system. The system uses a stereo camera to locate, track, and recognize a person's face. Our algorithm improves state-of-the-art monocular 2D object recognition techniques by additionally considering the facial 3D surface, which is relatively stable under different lighting conditions. First, faces are detected and their surfaces are reconstructed from the stereo images. Afterwards, a 3D face is composed by joining 2D image data and appropriate depth data. The 3D face is then decomposed into its principal components. The principal components are used to recognize a 3D face by comparing characteristics of the current face to those of known individuals in a database. The result is an efficient and accurate face recognition algorithm. To evaluate our approach, we compared its performance to a classical monocular face recognition algorithm and observed that the recognition rate increased on average by 7.7 percent.

We present a new cache oblivious scheme for iterative stencil computations that performs beyond system bandwidth limitations as though gigabytes of data could reside in an enormous on-chip cache. We compare execution times for 2D and 3D spatial domains with up to 128 million double precision elements for constant and variable stencils against hand-optimized naive code and the automatic polyhedral parallelizer and locality optimizer PluTo and demonstrate the clear superiority of our results.

In this paper a method for estimating a rigid skeleton, including skinning weights, skeleton connectivity, and joint positions, given a sparse set of example poses is presented. In contrast to other methods, we are able to simultaneously take examples of different subjects into account, which improves the robustness of the estimation. It is additionally possible to generate a skeleton that primarily describes variations in body shape instead of pose. The shape skeleton can then be combined with a regular pose varying skeleton. That way pose and body shape can be controlled simultaneously but separately. As this skeleton is technically still just a skinned rigid skeleton, compatibility with major modelling packages and game engines is retained. We further present an approach for synthesizing a suitable bind shape that additionally improves the accuracy of the generated model.

Pixel processing is becoming increasingly expensive for real-time applications due to the complexity of today's shaders and high-resolution framebuffers. However, most shading results are spatially or temporally coherent, which allows for sparse sampling and reuse of neighboring pixel values. This paper proposes a simple framework for spatio-temporal upsampling on modern GPUs. In contrast to previous work, which focuses either on temporal or spatial processing on the GPU, we exploit coherence in both. Our algorithm combines adaptive motion-compensated filtering over time and geometry-aware upsampling in image space. It is robust with respect to high-frequency temporal changes, and achieves substantial performance improvements by limiting the number of recomputed samples per frame. At the same time, we increase the quality of spatial upsampling by recovering missing information from previous frames. This temporal strategy also allows us to ensure that the image converges to a higher quality result.

Volume caustics are intricate illumination patterns formed by light first interacting with a specular surface and subsequently being scattered inside a participating medium. Although this phenomenon can be simulated by existing techniques, image synthesis is usually non-trivial and time-consuming.

Abstract We present physically based algorithms for interactive deformable shape and motion modelling. We coarsely sample the objects with simulation nodes, and apply a meshless finite element method to obtain realistic deformations at interactive frame rates. This shape deformation algorithm is then used to specify keyframe poses and a smooth interpolating motion is obtained by solving for an energy‐minimizing trajectory. We show how to handle collisions between different deformable objects as well as with static or moving scene objects. Secondary motion is added as a post‐process by running a meshless elastic solid simulation. We enforce precomputed trajectories using control forces computed using shape matching. Key to the efficiency of our method is a sparse deformation representation and an adaptive optimization algorithm that automatically introduces new degrees of freedom in problematic regions. An accurate temporal interpolation scheme that exactly recovers rigid motions keeps the number of unknowns low and achieves realistic deformations with very few keyframes. We also show how the algorithm allows combining purely physical simulation with keyframe‐based scripted animation. The presented results illustrate that our framework can handle complex shapes at interactive rates, making it a valuable tool for animators to realistically model deformable 3D shapes and their motion.

Abstract High‐refresh‐rate displays (e. g., 120 Hz) have recently become available on the consumer market and quickly gain on popularity. One of their aims is to reduce the perceived blur created by moving objects that are tracked by the human eye. However, an improvement is only achieved if the video stream is produced at the same high refresh rate (i. e. 120 Hz). Some devices, such as LCD TVs, solve this problem by converting low‐refresh‐rate content (i. e. 50 Hz PAL) into a higher temporal resolution (i. e. 200 Hz) based on two‐dimensional optical flow. In our approach, we will show how rendered three‐dimensional images produced by recent graphics hardware can be up‐sampled more efficiently resulting in higher quality at the same time. Our algorithm relies on several perceptual findings and preserves the naturalness of the original sequence. A psychophysical study validates our approach and illustrates that temporally up‐sampled video streams are preferred over the standard low‐rate input by the majority of users. We show that our solution improves task performance on high‐refresh‐rate displays.

Abstract We present variance soft shadow mapping (VSSM) for rendering plausible soft shadow in real‐time. VSSM is based on the theoretical framework of percentage‐closer soft shadows (PCSS) and exploits recent advances in variance shadow mapping (VSM). Our new formulation allows for the efficient computation of (average) blocker distances, a common bottleneck in PCSS‐based methods. Furthermore, we avoid incorrectly lit pixels commonly encountered in VSM‐based methods by appropriately subdividing the filter kernel. We demonstrate that VSSM renders high‐quality soft shadows efficiently (usually over 100 fps) for complex scene settings. Its speed is at least one order of magnitude faster than PCSS for large penumbra.

Local optimization and filtering have been widely applied to model-based 3D human motion capture. Global stochastic optimization has recently been proposed as promising alternative solution for tracking and initialization. In order to benefit from optimization and filtering, we introduce a multi-layer framework that combines stochastic optimization, filtering, and local optimization. While the first layer relies on interacting simulated annealing and some weak prior information on physical constraints, the second layer refines the estimates by filtering and local optimization such that the accuracy is increased and ambiguities are resolved over time without imposing restrictions on the dynamics. In our experimental evaluation, we demonstrate the significant improvements of the multi-layer framework and provide quantitative 3D pose tracking results for the complete HumanEva-II dataset. The paper further comprises a comparison of global stochastic optimization with particle filtering, annealed particle filtering, and local optimization.

Numerous image processing and computer graphics methods make use of either explicitly computed strength of image edges, or an implicit edge strength definition that is integrated into their algorithms. In both cases, the end result is highly affected by the computation of edge strength. We address several shortcomings of the widely used gradient magnitude-based edge strength model through the computation of a hypothetical Human Visual System (HVS) response at edge locations. Contrary to gradient magnitude, the resulting “visual significance” values account for various HVS mechanisms such as luminance adaptation and visual masking, and are scaled in perceptually linear units that are uniform across images. The visual significance computation is implemented in a fast multiscale second-generation wavelet framework which we use to demonstrate the differences in image retargeting, HDR image stitching, and tone mapping applications with respect to the gradient magnitude model. Our results suggest that simple perceptual models provide qualitative improvements on applications utilizing edge strength at the cost of a modest computational burden.

Numerous current Computer Graphics methods produce video sequences as their outcome. The merit of these methods is often judged by assessing the quality of a set of results through lengthy user studies. We present a full-reference video quality metric geared specifically towards the requirements of Computer Graphics applications as a faster computational alternative to subjective evaluation. Our metric can compare a video pair with arbitrary dynamic ranges, and comprises a human visual system model for a wide range of luminance levels, that predicts distortion visibility through models of luminance adaptation, spatiotemporal contrast sensitivity and visual masking. We present applications of the proposed metric to quality prediction of HDR video compression and temporal tone mapping, comparison of different rendering approaches and qualities, and assessing the impact of variable frame rate to perceived quality.

In this paper, we address the problem of inverse procedural modeling: Given a piece of exemplar 3D geometry, we would like to find a set of rules that describe objects that are similar to the exemplar. We consider local similarity, i.e., each local neighborhood of the newly created object must match some local neighborhood of the exemplar. We show that we can find explicit shape modification rules that guarantee strict local similarity by looking at the structure of the partial symmetries of the object. By cutting the object into pieces along curves within symmetric areas, we can build shape operations that maintain local similarity by construction. We systematically collect such editing operations and analyze their dependency to build a shape grammar. We discuss how to extract general rewriting systems, context free hierarchical rules, and grid-based rules. All of this information is derived directly from the model, without user interaction. The extracted rules are then used to implement tools for semi-automatic shape modeling by example, which are demonstrated on a number of different example data sets. Overall, our paper provides a concise theoretical and practical framework for inverse procedural modeling of 3D objects.

Limited spatial resolution of current displays makes the depiction of very fine spatial details difficult. This work proposes a novel method applied to moving images that takes into account the human visual system and leads to an improved perception of such details. To this end, we display images rapidly varying over time along a given trajectory on a high refresh rate display. Due to the retinal integration time the information is fused and yields apparent super-resolution pixels on a conventional-resolution display. We discuss how to find optimal temporal pixel variations based on linear eye-movement and image content and extend our solution to arbitrary trajectories. This step involves an efficient method to predict and successfully treat potentially visible flickering. Finally, we evaluate the resolution enhancement in a perceptual study that shows that significant improvements can be achieved both for computer generated images and photographs.

In fluorescent materials, light from a certain band of incident wavelengths is reradiated at longer wavelengths, i.e., with a reduced per-photon energy. While fluorescent materials are common in everyday life, they have received little attention in computer graphics. Especially, no bidirectional reradiation measurements of fluorescent materials have been available so far. In this paper, we extend the well-known concept of the bidirectional reflectance distribution function (BRDF) to account for energy transfer between wavelengths, resulting in a Bispectral Bidirectional Reflectance and Reradiation Distribution Function (bispectral BRRDF). Using a bidirectional and bispectral measurement setup, we acquire reflectance and reradiation data of a variety of fluorescent materials, including vehicle paints, paper and fabric, and compare their renderings with RGB, RGBxRGB, and spectral BRDFs. Our acquisition is guided by a principal component analysis on complete bispectral data taken under a sparse set of angles. We show that in order to faithfully reproduce the full bispectral information for all other angles, only a very small number of wavelength pairs needs to be measured at a high angular resolution.

We present a system for quick and easy manipulation of the body shape and proportions of a human actor in arbitrary video footage. The approach is based on a morphable model of 3D human shape and pose that was learned from laser scans of real people. The algorithm commences by spatio-temporally fitting the pose and shape of this model to the actor in either single-view or multi-view video footage. Once the model has been fitted, semantically meaningful attributes of body shape, such as height, weight or waist girth, can be interactively modified by the user. The changed proportions of the virtual human model are then applied to the actor in all video frames by performing an image-based warping. By this means, we can now conveniently perform spatio-temporal reshaping of human actors in video footage which we show on a variety of video sequences.

We present a novel rendering system for defocus blur and lens effects. It supports physically-based rendering and outperforms previous approaches by involving a novel GPU-based tracing method. Our solution achieves more precision than competing real-time solutions and our results are mostly indistinguishable from offline rendering. Our method is also more general and can integrate advanced simulations, such as simple geometric lens models enabling various lens aberration effects. These latter is crucial for realism, but are often employed in artistic contexts, too. We show that available artistic lenses can be simulated by our method. In this spirit, our work introduces an intuitive control over depth-of-field effects. The physical basis is crucial as a starting point to enable new artistic renderings based on a generalized focal surface to emphasize particular elements in the scene while retaining a realistic look. Our real-time solution provides realistic, as well as plausible expressive results.

We present an interactive system for the artistic control of visual phenomena visible on surfaces. Our method allows the user to intuitively reposition shadows, caustics, and indirect illumination using a simple click-and-drag user interface working directly on surfaces. In contrast to previous approaches, the positions of the lights or objects in the scene remain unchanged, enabling localized edits of individual shading components. Our method facilitates the editing by computing a mapping from one surface location to another. Based on this mapping, we can not only edit shadows, caustics, and indirect illumination but also other surface properties, such as color or texture, in a unified way. This is achieved using an intuitive user-interface that allows the user to specify position constraints with drag-and-drop or sketching operations directly on the surface. Our approach requires no explicit surface parametrization and handles scenes with arbitrary topology. We demonstrate the applicability of the approach to interactive editing of shadows, reflections, refractions, textures, caustics, and diffuse indirect light. The effectiveness of the system to achieve an artistic goal is evaluated by a user study.

This paper presents data-parallel algorithms for surface and solid voxelization on graphics hardware. First, a novel conservative surface voxelization technique, setting all voxels overlapped by a mesh's triangles, is introduced, which is up to one order of magnitude faster than previous solutions leveraging the standard rasterization pipeline. We then show how the involved new triangle/box overlap test can be adapted to yield a 6-separating surface voxelization, which is thinner but still connected and gap-free. Complementing these algorithms, both a triangle-parallel and a tile-based technique for solid voxelization are subsequently presented. Finally, addressing the high memory consumption of high-resolution voxel grids, we introduce a novel octree-based sparse solid voxelization approach, where only close to the solid's boundary finest-level voxels are stored, whereas uniform interior and exterior regions are represented by coarser-level voxels. This representation is created directly from a mesh without requiring a full intermediate solid voxelization, enabling GPU-based voxelizations of unprecedented size.

Crease surfaces are two-dimensional manifolds along which a scalar field assumes a local maximum (ridge) or a local minimum (valley) in a constrained space. Unlike isosurfaces, they are able to capture extremal structures in the data. Creases have a long tradition in image processing and computer vision, and have recently become a popular tool for visualization. When extracting crease surfaces, degeneracies of the Hessian (i.e., lines along which two eigenvalues are equal) have so far been ignored. We show that these loci, however, have two important consequences for the topology of crease surfaces: First, creases are bounded not only by a side constraint on eigenvalue sign, but also by Hessian degeneracies. Second, crease surfaces are not, in general, orientable. We describe an efficient algorithm for the extraction of crease surfaces which takes these insights into account and demonstrate that it produces more accurate results than previous approaches. Finally, we show that diffusion tensor magnetic resonance imaging (DT-MRI) stream surfaces, which were previously used for the analysis of planar regions in diffusion tensor MRI data, are mathematically ill-defined. As an example application of our method, creases in a measure of planarity are presented as a viable substitute.

This paper proposes a method for capturing the performance of a human or an animal from a multi-view video sequence. Given an articulated template model and silhouettes from a multi-view image sequence, our approach recovers not only the movement of the skeleton, but also the possibly non-rigid temporal deformation of the 3D surface. While large scale deformations or fast movements are captured by the skeleton pose and approximate surface skinning, true small scale deformations or non-rigid garment motion are captured by fitting the surface to the silhouette. We further propose a novel optimization scheme for skeleton-based pose estimation that exploits the skeleton's tree structure to split the optimization problem into a local one and a lower dimensional global one. We show on various sequences that our approach can capture the 3D motion of animals and humans accurately even in the case of rapid movements and wide apparel like skirts.

We present an approach for recovering the reflectance of a static scene with known geometry from a collection of images taken under distant, unknown illumination. In contrast to previous work, we allow the illumination to vary between the images, which greatly increases the applicability of the approach. Using an all-frequency relighting framework based on wavelets, we are able to simultaneously estimate the per-image incident illumination and the persurface point reflectance. The wavelet framework allows for incorporating various reflection models. We demonstrate the quality of our results for synthetic test cases as well as for several datasets captured under laboratory conditions. Combined with multi-view stereo reconstruction, we are even able to recover the geometry and reflectance of a scene solely using images collected from the Internet.

In this work we present an approach for markerless motion capture (MoCap) of articulated objects, which are recorded with multiple unsynchronized moving cameras. Instead of using fixed (and expensive) hardware synchronized cameras, this approach allows us to track people with off-the-shelf handheld video cameras. To prepare a sequence for motion capture, we first reconstruct the static background and the position of each camera using Structure-from-Motion (SfM). Then the cameras are registered to each other using the reconstructed static background geometry. Camera synchronization is achieved via the audio streams recorded by the cameras in parallel. Finally, a markerless MoCap approach is applied to recover positions and joint configurations of subjects. Feature tracks and dense background geometry are further used to stabilize the MoCap. The experiments show examples with highly challenging indoor and outdoor scenes.

This paper introduces a new shape matching algorithm for computing correspondences between 3D surfaces that have undergone (approximately) isometric deformations. The new approach makes two main contributions: First, the algorithm is, unlike previous work, robust to “topological noise” such as large holes or “false connections”, which is both observed frequently in real-world scanner data. Second, our algorithm samples the space of feasible solutions such that uncertainty in matching can be detected explicitly. We employ a novel randomized feature matching algorithm in order to find robust subsets of geodesics to verify isometric consistency. The paper shows shape matching results for real world and synthetic data sets that could not be handled using previous deformable matching algorithms.

In this paper, we introduce a novel iterative motion tracking framework that combines 3D tracking techniques with motion retrieval for stabilizing markerless human motion capturing. The basic idea is to start human tracking without prior knowledge about the performed actions. The resulting 3D motion sequences, which may be corrupted due to tracking errors, are locally classified according to available motion categories. Depending on the classification result, a retrieval system supplies suitable motion priors, which are then used to regularize and stabilize the tracking in the next iteration step. Experiments with the HumanEVA-II benchmark show that tracking and classification are remarkably improved after few iterations.

In this paper, we present a novel algorithm for partial intrinsic symmetry detection in 3D geometry. Unlike previous work, our algorithm is based on a conceptually simple and straightforward probabilistic formulation of partial shape matching: based on a Markov random field model, we obtain a probability distribution over all possible intrinsic matches of a shape to itself, which reveals the symmetry structure of the object. Rather than examining this exponentially sized distribution directly, which is infeasible, we approximate marginals of this distribution using sum-product loopy belief propagation and show how the symmetry information can subsequently be extracted from this condensed representation. Using a parallel implementation on graphics hardware, we are able to extract symmetries of deformable shapes in general poses efficiently. We apply our algorithm on several standard 3D models, demonstrating that a concise probabilistic model yields a practical and general symmetry detection algorithm.

This paper presents a real-time face detection algorithm. It improves state-of-the-art 2D object detection techniques by additionally evaluating a disparity map, which is estimated for the face region using a calibrated stereo camera setup. First, faces are detected in the 2D images with a rapid object classifier based on haar-like features. In a second step, falsely detected faces are removed by analyzing the disparity map. In the near field of the camera, a classifier is used, which evaluates the Eigenfaces of the normalized disparity map. Thereby, the transformation into Eigenspace is learned off-line using a principal component analysis approach. In the far field, a much simpler approach determines false-positives by evaluating the relationship between the size of the face in the image and its distance to the camera. This novel combination of algorithms runs in real-time and significantly reduces the number of false-positives compared to classical 2D face detection approaches.

Physically plausible illumination at real-time framerates is often achieved using approximations. One popular example is ambient occlusion (AO), for which very simple and efficient implementations are used extensively in production. Recent methods approximate AO between nearby geometry in screen space (SSAO). The key observation described in this paper is, that screen-space occlusion methods can be used to compute many more types of effects than just occlusion, such as directional shadows and indirect color bleeding. The proposed generalization has only a small overhead compared to classic SSAO, approximates direct and one-bounce light transport in screen space, can be combined with other methods that simulate transport for macro structures and is visually equivalent to SSAO in the worst case without introducing new artifacts. Since our method works in screen space, it does not depend on the geometric complexity. Plausible directional occlusion and indirect lighting effects can be displayed for large and fully dynamic scenes at real-time frame rates.

Among all forms of sculpture, bas-relief is arguably the closest to painting. Although inherently a two dimensional sculpture, a bas-relief suggests a visual spatial extension of the scene in depth through the combination of composition, perspective, and shading. There have been significant results on digital bas-relief generation but many of the existing techniques may wash out high level surface detail during the compression process. The primary goal of this work is to address the problem of fine features by tailoring a filtering technique that achieves good compression without compromising the quality of surface details. As a secondary application we explore the generation of artistic relief which mimic cubism in painting and we show how it could be used for generating Picasso like portraits.

This work addresses the problem of tracking humans with skeleton-based shape models where video footage is acquired by multiple cameras. Since the shape deformations are parameterized by the skeleton, the position, orientation, and configuration of the human skeleton are estimated such that the deformed shape model is best explained by the image data. To solve this problem, several algorithms have been proposed over the last years. The approaches usually rely on filtering, local optimization, or global optimization. The global optimization algorithms can be further divided into single hypothesis (SHO) and multiple hypothesis optimization (MHO). We briefly compare the underlying mathematical models and evaluate the performance of one representative algorithm for each class. Furthermore, we compare several likelihoods and parameter settings with respect to accuracy and computation cost. A thorough evaluation is performed on two sequences with uncontrolled lighting conditions and non-static background. In addition, we demonstrate the impact of the likelihood on the HumanEva benchmark. Our results provide a guidance on algorithm design for different applications related to human motion capture.

Abstract Display devices, more than ever, are finding their ways into electronic consumer goods as a result of recent trends in providing more functionality and user interaction. Combined with the new developments in display technology towards higher reproducible luminance range, the mobility and variation in capability of display devices are constantly increasing. Consequently, in real life usage it is now very likely that the display emission to be distorted by spatially and temporally varying reflections, and the observer's visual system to be not adapted to the particular display that she is viewing at that moment. The actual perception of the display content cannot be fully understood by only considering steady‐state illumination and adaptation conditions. We propose an objective method for display visibility analysis formulating the problem as a full‐reference image quality assessment problem, where the display emission under “ideal” conditions is used as the reference for real‐life conditions. Our work includes a human visual system model that accounts for maladaptation and temporal recovery of sensitivity. As an example application we integrate our method to a global illumination simulator and analyze the visibility of a car interior display under realistic lighting conditions.

Abstract In this paper, we describe a new algorithm for detecting structural redundancy in geometric data sets. Our algorithm computes rigid symmetries, i.e., subsets of a surface model that reoccur several times within the model differing only by translation, rotation or mirroring. Our algorithm is based on matching locally coherent constellations of feature lines on the object surfaces. In comparison to previous work, the new algorithm is able to detect a large number of symmetric parts without restrictions to regular patterns or nested hierarchies. In addition, working on relevant features only leads to a strong reduction in memory and processing costs such that very large data sets can be handled. We apply the algorithm to a number of real world 3D scanner data sets, demonstrating high recognition rates for general patterns of symmetry.

Abstract Generation and animation of realistic humans is an essential part of many projects in today's media industry. Especially, the games and special effects industry heavily depend on realistic human animation. In this work a unified model that describes both, human pose and body shape is introduced which allows us to accurately model muscle deformations not only as a function of pose but also dependent on the physique of the subject. Coupled with the model's ability to generate arbitrary human body shapes, it severely simplifies the generation of highly realistic character animations. A learning based approach is trained on approximately 550 full body 3D laser scans taken of 114 subjects. Scan registration is performed using a non‐rigid deformation technique. Then, a rotation invariant encoding of the acquired exemplars permits the computation of a statistical model that simultaneously encodes pose and body shape. Finally, morphing or generating meshes according to several constraints simultaneously can be achieved by training semantically meaningful regressors.

Abstract Computing global illumination in complex scenes is even with todays computational power a demanding task. In this work we propose a novel irradiance caching scheme that combines the advantages of two state‐of‐the‐art algorithms for high‐quality global illumination rendering:lightcuts, an adaptive and hierarchical instant‐radiosity based algorithm and the widely used (ir)radiance caching algorithm for sparse sampling and interpolation of (ir)radiance in object space. Our adaptive radiance caching algorithm is based on anisotropic cache splatting, which adapts the cache footprints not only to the magnitude of the illumination gradient computed with light‐cuts but also to its orientation allowing larger interpolation errors along the direction of coherent illumination while reducing the error along the illumination gradient. Since lightcuts computes the direct and indirect lighting seamlessly, we use a two‐layer radiance cache, to store and control the interpolation of direct and indirect lighting individually with different error criteria. In multiple iterations our method detects cache interpolation errors above the visibility threshold of a pixel and reduces the anisotropic cache footprints accordingly. We achieve significantly better image quality while also speeding up the computation costs by one to two orders of magnitude with respect to the well‐known photon mapping with (ir)radiance caching procedure.

Abstract We propose a system that allows the user to design a continuous flow animation starting from a still fluid image. The basic idea is to apply the fluid motion extracted from a video example to the target image. The system first decomposes the video example into three components, an average image, a flow field and residuals. The user then specifies equivalent information over the target image. The user manually paints the rough flow field, and the system automatically refines it using the estimated gradients of the target image. The user semi‐automatically transfers the residuals onto the target image. The system then approximates the average image and synthesizes an animation on the target image by adding the transferred residuals and warping them according to the user‐specified flow field. Finally, the system adjusts the appearance of the resulting animation by applying histogram matching. We designed animations of various pictures, such as rivers, waterfalls, fires, and smoke.

Abstract Glare is a consequence of light scattered within the human eye when looking at bright light sources. This effect can be exploited for tone mapping since adding glare to the depiction of high‐dynamic range (HDR) imagery on a low‐dynamic range (LDR) medium can dramatically increase perceived contrast. Even though most, if not all, subjects report perceiving glare as a bright pattern that fluctuates in time, up to now it has only been modeled as a static phenomenon. We argue that the temporal properties of glare are a strong means to increase perceived brightness and to produce realistic and attractive renderings of bright light sources. Based on the anatomy of the human eye, we propose a model that enables real‐time simulation of dynamic glare on a GPU. This allows an improved depiction of HDR images on LDR media for interactive applications like games, feature films, or even by adding movement to initially static HDR images. By conducting psychophysical studies, we validate that our method improves perceived brightness and that dynamic glare‐renderings are often perceived as more attractive depending on the chosen scene.

Abstract While there are various commercial‐strength editing tools available today for still images, object‐based manipulation of real‐world video footage is still a challenging problem. In this system paper, we present a framework for interactive video editing. Our focus is on footage from a single, conventional video camera. By relying on spatio‐temporal editing techniques operating on the video cube, we do not need to recover 3D scene geometry. Our framework is capable of removing and inserting objects, object motion editing, non‐rigid object deformations, keyframe interpolation, as well as emulating camera motion. We demonstrate how movie shots with moderate complexity can be persuasively modified during post‐processing.

We present a GPU-based real-time rendering method that simulates high-quality depth-of-field effects, similar in quality to multiview accumulation methods. Most real-time approaches have difficulties to obtain good approximations of visibility and view-dependent shading due to the use of a single view image. Our method also avoids the multiple rendering of a scene, but can approximate different views by relying on a layered image-based scene representation. We present several performance and quality improvements, such as early culling, approximate cone tracing, and jittered sampling. Our method achieves artifact-free results for complex scenes and reasonable depth-of-field blur in real time.

Recent approaches to global illumination for dynamic scenes achieve interactive frame rates by using coarse approximations to geometry, lighting, or both, which limits scene complexity and rendering quality. High-quality global illumination renderings of complex scenes are still limited to methods based on ray tracing. While conceptually simple, these techniques are computationally expensive. We present an efficient and scalable method to compute global illumination solutions at interactive rates for complex and dynamic scenes. Our method is based on parallel final gathering running entirely on the GPU. At each final gathering location we perform micro-rendering: we traverse and rasterize a hierarchical point-based scene representation into an importance-warped micro-buffer , which allows for BRDF importance sampling. The final reflected radiance is computed at each gathering location using the micro-buffers and is then stored in image-space. We can trade quality for speed by reducing the sampling rate of the gathering locations in conjunction with bilateral upsampling. We demonstrate the applicability of our method to interactive global illumination, the simulation of multiple indirect bounces, and to final gathering from photon maps.

Effective digital content creation tools must be both efficient in the interactions they provide but also allow full user control. There may be occasions, when art direction requires changes that contradict physical laws. In particular, it is known that physical correctness of reflections for the human observer is hard to assess. For many centuries, traditional artists have exploited this fact to depict reflections that lie outside the realm of physical possibility. However, a system that gives explicit control of this effect to digital artists has not yet been described. This paper introduces a system that transforms physically correct reflections into art-directed reflections, as specified by reflection constraints . The system introduces a taxonomy of reflection editing operations, using an intuitive user interface, that works directly on the reflecting surfaces with real-time visual feedback using a GPU. A user study shows how such a system can allow users to quickly manipulate reflections according to an art direction task.

We present a new technique for reconstructing a single shape and its nonrigid motion from 3D scanning data. Our algorithm takes a set of time-varying unstructured sample points that capture partial views of a deforming object as input and reconstructs a single shape and a deformation field that fit the data. This representation yields dense correspondences for the whole sequence, as well as a completed 3D shape in every frame. In addition, the algorithm automatically removes spatial and temporal noise artifacts and outliers from the raw input data. Unlike previous methods, the algorithm does not require any shape template but computes a fitting shape automatically from the input data. Our reconstruction framework is based upon a novel topology-aware adaptive subspace deformation technique that allows handling long sequences with complex geometry efficiently. The algorithm accesses data in multiple sequential passes, so that long sequences can be streamed from hard disk, not being limited by main memory. We apply the technique to several benchmark datasets, significantly increasing the complexity of the data that can be handled efficiently in comparison to previous work.

Temporal coherence is crucial in content-aware video retargeting. To date, this problem has been addressed by constraining temporally adjacent pixels to be transformed coherently. However, due to the motion-oblivious nature of this simple constraint, the retargeted videos often exhibit flickering or waving artifacts, especially when significant camera or object motions are involved. Since the feature correspondence across frames varies spatially with both camera and object motion, motion-aware treatment of features is required for video resizing. This motivated us to align consecutive frames by estimating interframe camera motion and to constrain relative positions in the aligned frames. To preserve object motion, we detect distinct moving areas of objects across multiple frames and constrain each of them to be resized consistently. We build a complete video resizing framework by incorporating our motion-aware constraints with an adaptation of the scale-and-stretch optimization recently proposed by Wang and colleagues. Our streaming implementation of the framework allows efficient resizing of long video sequences with low memory cost. Experiments demonstrate that our method produces spatiotemporally coherent retargeting results even for challenging examples with complex camera and object motion, which are difficult to handle with previous techniques.

Modern experimental and computational fluid mechanics are increasingly concerned with the structure nature of fluid motion. Recent research has highlighted the analysis of one transport structure which is called Lagrangian coherent structure. However, the quantity nature of the flow transport is still unclear. In this paper, we focus on the transport characteristics of physical quantities and propose an approach to visualize the finite-time transport structure of quantity advection. This is similar to an integral convolution over a scalar field along path-lines of a flow field. Applied to a well-chosen set of physical quantity fields this yields structures giving insights into the dynamical processes of the underlying flow. We demonstrate our approach on a number of test data sets.

This paper describes a new passive approach to capture time-varying scene geometry in large acquisition volumes from multi-view video. It can be applied to reconstruct complete moving models of human actors that feature even slightest dynamic geometry detail, such as wrinkles and folds in clothing, and that can be viewed from 360deg. Starting from multi-view video streams recorded under calibrated lighting, we first perform marker-less human motion capture based on a smooth template with no high-frequency surface detail. Subsequently, surface reflectance and time-varying normal fields are estimated based on the coarse template shape. The main contribution of this paper is a new statistical approach to solve the non-trivial problem of transforming the captured normal field that is defined over the smooth non-planar 3D template into true 3D displacements. Our spatio-temporal reconstruction method outputs displaced geometry that is accurate at each time step of video and temporally smooth, even if the input data are affected by noise.

We present a dense 3D correspondence finding method that enables spatio-temporally coherent reconstruction of surface animations from multi-view video data. Given as input a sequence of shape-from-silhouette volumes of a moving subject that were reconstructed for each time frame individually, our method establishes dense surface correspondences between subsequent shapes independently of surface discretization. This is achieved in two steps: first, we obtain sparse correspondences from robust optical features between adjacent frames. Second, we generate dense correspondences which serve as map between respective surfaces. By applying this procedure subsequently to all pairs of time steps we can trivially align one shape with all others. Thus, the original input can be reconstructed as a sequence of meshes with constant connectivity and small tangential distortion. We exemplify the performance and accuracy of our method using several synthetic and captured real-world sequences.

Most digital cameras capture color pictures in the form of an image mosaic, recording only one color channel at each pixel position. Therefore, an interpolation algorithm needs to be applied to reconstruct the missing color information. In this paper we present a novel Bayer pattern demosaicing approach, employing stochastic global optimization performed on a pixel neighborhood. We are minimizing a newly developed cost function that increases smoothness along one-dimensional image features. While previous algorithms have been developed focusing on LDR images only, our optimization scheme and the underlying cost function are designed to handle both LDR and HDR images, creating less demosaicing artifacts, compared to previous approaches.

We present a new 3D scanning method using modulated phase-shifting. Optical scanning of complex objects or scenes with significant global light transport, such as subsurface scattering, interreflections, volumetric scattering, etc. is a difficult task since the direct surface reflection will be mixed with the global illumination. The direct and global components can be effficiently separated using high frequency illumination which to some extend is done in traditional phase-shifting for 3D scanning. In this paper we introduce the concept of modulation based separation where a high frequency signal is multiplied on top of other signal. The modulated signal inherits the good separation properties of the high frequency signal and allows for removing artifacts due to global illumination. This technique can be used to clean up arbitrary projected signals, e.g. photographs as well as the sinusoid patterns used for phase-shifting. For the modulated phase-shifting, we propose a two-pass separation method exploiting high frequency patterns in two-dimensions that can filter out the global components much more completely than traditional one-pass separation methods. We demonstrate the effectiveness of our approach on a couple of scenes with significant subsurface scattering and interreflections.

Model-based 3D tracker estimate the position, rotation, and joint angles of a given model from video data of one or multiple cameras. They often rely on image features that are tracked over time but the accumulation of small errors results in a drift away from the target object. In this work, we address the drift problem for the challenging task of human motion capture and tracking in the presence of multiple moving objects where the error accumulation becomes even more problematic due to occlusions. To this end, we propose an analysis-by-synthesis framework for articulated models. It combines the complementary concepts of patch-based and region-based matching to track both structured and homogeneous body parts. The performance of our method is demonstrated for rigid bodies, body parts, and full human bodies where the sequences contain fast movements, self-occlusions, multiple moving objects, and clutter. We also provide a quantitative error analysis and comparison with other model-based approaches.

This work deals with modeling and markerless tracking of athletes interacting with sports gear. In contrast to classical markerless tracking, the interaction with sports gear comes along with joint movement restrictions due to additional constraints: while humans can generally use all their joints, interaction with the equipment imposes a coupling between certain joints. A cyclist who performs a cycling pattern is one example: The feet are supposed to stay on the pedals, which are again restricted to move along a circular trajectory in 3D-space. In this paper, we present a markerless motion capture system that takes the lower-dimensional pose manifold into account by modeling the motion restrictions via soft constraints during pose optimization. Experiments with two different models, a cyclist and a snowboarder, demonstrate the applicability of the method. Moreover, we present motion capture results for challenging outdoor scenes including shadows and strong illumination changes.

This paper presents a GPU-based, fast, and accurate dynamic height field rendering technique that scales well to large scale height fields. Current real-time rendering algorithms for dynamic height fields employ approximate ray-height field intersection methods, whereas accurate algorithms require pre-computation in the order of seconds to minutes and are thus not suitable for dynamic height field rendering. We alleviate this problem by using maximum mipmaps, a hierarchical data structure supporting accurate and efficient rendering while simultaneously lowering the pre-computation costs to negligible levels. Furthermore, maximum mipmaps allow for view-dependent level-of-detail rendering. In combination with hierarchical ray-stepping this results in an efficient intersection algorithm for large scale height fields.

Quadrangular remeshing of triangulated surfaces has received an increasing attention in recent years. A particularly elegant approach is the extraction of quads from the streamlines of a harmonic field. While the construction of such fields is by now a standard technique in geometry processing, enforcing design constraints is still not fully investigated. This work presents a technique for handling directional constraints by directly controlling the gradient of the field. In this way, line constraints sketched by the user or automatically obtained as feature lines can be fulfilled efficiently. Furthermore, we show the potential of quasi-harmonic fields as a flexible tool for controlling the behavior of the field over the surface. Treating the surface as an inhomogeneous domain we can endow specific surface regions with field attraction/repulsion properties.

Abstract Recently, it has become increasingly popular to represent animations not by means of a classical skeleton‐based model, but in the form of deforming mesh sequences. The reason for this new trend is that novel mesh deformation methods as well as new surface based scene capture techniques offer a great level of flexibility during animation creation. Unfortunately, the resulting scene representation is less compact than skeletal ones and there is not yet a rich toolbox available which enables easy post‐processing and modification of mesh animations. To bridge this gap between the mesh‐based and the skeletal paradigm, we propose a new method that automatically extracts a plausible kinematic skeleton, skeletal motion parameters, as well as surface skinning weights from arbitrary mesh animations. By this means, deforming mesh sequences can be fully‐automatically transformed into fullyrigged virtual subjects. The original input can then be quickly rendered based on the new compact bone and skin representation, and it can be easily modified using the full repertoire of already existing animation tools.

Abstract To utilize the full potential of new high dynamic range (HDR) displays, a system for the enhancement of bright luminous objects in video sequences is proposed. The system classifies clipped (saturated) regions as lights, reflections or diffuse surfaces using a semi‐automatic classifier and then enhances each class of objects with respect to its relative brightness. The enhancement algorithm can significantly stretch the contrast of clipped regions while avoiding amplification of noise and contouring. We demonstrate that the enhanced video is strongly preferred to non‐enhanced video, and it compares favorably to other methods.

Abstract We present an implementation approach for Marching Cubes (MC) on graphics hardware for OpenGL 2.0 or comparable graphics APIs. It currently outperforms all other known graphics processing units (GPU)‐based iso‐surface extraction algorithms in direct rendering for sparse or large volumes, even those using the recently introduced geometry shader (GS) capabilites. To achieve this, we outfit the Histogram Pyramid (HP) algorithm, previously only used in GPU data compaction, with the capability for arbitrary data expansion. After reformulation of MC as a data compaction and expansion process, the HP algorithm becomes the core of a highly efficient and interactive MC implementation. For graphics hardware lacking GSs, such as mobile GPUs, the concept of HP data expansion is easily generalized, opening new application domains in mobile visual computing. Further, to serve recent developments, we present how the HP can be implemented in the parallel programming language CUDA (compute unified device architecture), by using a novel 1D chunk/layer construction.

Abstract In translucent objects, light paths are affected by multiple scattering, which is polluting any observation. Confocal imaging reduces the influence of such global illumination effects by carefully focusing illumination and viewing rays from a large aperture to a specific location within the object volume. The selected light paths still contain some global scattering contributions, though. Descattering based on high frequency illumination serves the same purpose. It removes the global component from observed light paths. We demonstrate that confocal imaging and descattering are orthogonal and propose a novel descattering protocol that analyzes the light transport in a neighborhood of light transport paths. In combination with confocal imaging, our descattering method achieves optical sectioning in translucent media with higher contrast and better resolution.

Abstract Currently 3D animation rendering and video compression are completely independent processes even if rendered frames are streamed on‐the‐fly within a client‐server platform. In such scenario, which may involve time‐varying transmission bandwidths and different display characteristics at the client side, dynamic adjustment of the rendering quality to such requirements can lead to a better use of server resources. In this work, we present a framework where the renderer and MPEG codec are coupled through a straightforward interface that provides precise motion vectors from the rendering side to the codec and perceptual error thresholds for each pixel in the opposite direction. The perceptual error thresholds take into account bandwidth‐dependent quantization errors resulting from the lossy com‐pression as well as image content‐dependent luminance and spatial contrast masking. The availability of the discrete cosine transform (DCT) coefficients at the codec side enables to use advanced models of the human visual system (HVS) in the perceptual error threshold derivation without incurring any significant cost. Those error thresholds are then used to control the rendering quality and make it well aligned with the compressed stream quality. In our prototype system we use the lightcuts technique developed by Walter et al., which we enhance to handle dynamic image sequences, and an MPEG‐2 implementation. Our results clearly demonstrate many advantages of coupling the rendering with video compression in terms of faster rendering. Furthermore, temporally coherent rendering leads to a reduction of temporal artifacts.

Abstract In recent years, a wide range of generalized barycentric coordinates has been suggested. However, all of them lack control over derivatives. We show how the notion of barycentric coordinates can be extended to specify derivatives at control points. This is also known as Hermite interpolation. We introduce a method to modify existing barycentric coordinates to higher order barycentric coordinates and demonstrate, using higher order mean value coordinates, that our method, although conceptually simple and easy to implement, can be used to give easy and intuitive control at interactive frame rates over local space deformations such as rotations.

Abstract Although several new tone‐mapping operators are proposed each year, there is no reliable method to validate their performance or to tell how different they are from one another. In order to analyze and understand the behavior of tone‐mapping operators, we model their mechanisms by fitting a generic operator to an HDR image and its tone‐mapped LDR rendering. We demonstrate that the majority of both global and local tone‐mapping operators can be well approximated by computationally inexpensive image processing operations, such as a per‐pixel tone curve, a modulation transfer function and color saturation adjustment. The results produced by such a generic tone‐mapping algorithm are often visually indistinguishable from much more expensive algorithms, such as the bilateral filter. We show the usefulness of our generic tone‐mapper in backward‐compatible HDR image compression, the black‐box analysis of existing tone mapping algorithms and the synthesis of new algorithms that are combination of existing operators.

Abstract Fiber tracking is a standard tool to estimate the course of major white matter tracts from diffusion tensor magnetic resonance imaging (DT‐MRI) data. In this work, we aim at supporting the visual analysis of classical streamlines from fiber tracking by integrating context from anatomical data, acquired by aT1‐weighted MRI measurement. To this end, we suggest a novel visualization metaphor, which is based on data‐driven deformation of geometry and has been inspired by a technique for anatomical fiber preparation known as Klingler dissection. We demonstrate that our method conveys the relation between streamlines and surrounding anatomical features more effectively than standard techniques like slice images and direct volume rendering. The method works automatically, but its GPU‐based implementation allows for additional, intuitive interaction.

This paper proposes a new marker-less approach to capturing human performances from multi-view video. Our algorithm can jointly reconstruct spatio-temporally coherent geometry, motion and textural surface appearance of actors that perform complex and rapid moves. Furthermore, since our algorithm is purely meshbased and makes as few as possible prior assumptions about the type of subject being tracked, it can even capture performances of people wearing wide apparel, such as a dancer wearing a skirt. To serve this purpose our method efficiently and effectively combines the power of surface- and volume-based shape deformation techniques with a new mesh-based analysis-through-synthesis framework. This framework extracts motion constraints from video and makes the laser-scan of the tracked subject mimic the recorded performance. Also small-scale time-varying shape detail is recovered by applying model-guided multi-view stereo to refine the model surface. Our method delivers captured performance data at high level of detail, is highly versatile, and is applicable to many complex types of scenes that could not be handled by alternative marker-based or marker-free recording techniques.

Shadow computation in dynamic scenes under complex illumination is a challenging problem. Methods based on precomputation provide accurate, real-time solutions, but are hard to extend to dynamic scenes. Specialized approaches for soft shadows can deal with dynamic objects but are not fast enough to handle more than one light source. In this paper, we present a technique for rendering dynamic objects under arbitrary environment illumination, which does not require any precomputation. The key ingredient is a fast, approximate technique for computing soft shadows, which achieves several hundred frames per second for a single light source. This allows for approximating environment illumination with a sparse collection of area light sources and yields real-time frame rates.

Fluid simulation is one of the most active research areas in computer graphics. However, it remains difficult to obtain measurements of real fluid flows for validation of the simulated data. In this paper, we take a step in the direction of capturing flow data for such purposes. Specifically, we present the first time-resolved Schlieren tomography system for capturing full 3D, non-stationary gas flows on a dense volumetric grid. Schlieren tomography uses 2D ray deflection measurements to reconstruct a time-varying grid of 3D refractive index values, which directly correspond to physical properties of the flow. We derive a new solution for this reconstruction problem that lends itself to efficient algorithms that robustly work with relatively small numbers of cameras. Our physical system is easy to set up, and consists of an array of relatively low cost rolling-shutter camcorders that are synchronized with a new approach. We demonstrate our method with real measurements, and analyze precision with synthetic data for which ground truth information is available.

The diversity of display technologies and introduction of high dynamic range imagery introduces the necessity of comparing images of radically different dynamic ranges. Current quality assessment metrics are not suitable for this task, as they assume that both reference and test images have the same dynamic range. Image fidelity measures employed by a majority of current metrics, based on the difference of pixel intensity or contrast values between test and reference images, result in meaningless predictions if this assumption does not hold. We present a novel image quality metric capable of operating on an image pair where both images have arbitrary dynamic ranges. Our metric utilizes a model of the human visual system, and its central idea is a new definition of visible distortion based on the detection and classification of visible changes in the image structure. Our metric is carefully calibrated and its performance is validated through perceptual experiments. We demonstrate possible applications of our metric to the evaluation of direct and inverse tone mapping operators as well as the analysis of the image appearance on displays with various characteristics.

Traditional flat screen displays present 2D images. 3D and 4D displays have been proposed making use of lenslet arrays to shape a fixed outgoing light field for horizontal or bidirectional parallax. In this article, we present different designs of multi-dimensional displays which passively react to the light of the environment behind. The prototypes physically implement a reflectance field and generate different light fields depending on the incident illumination, for example light falling through a window. We discretize the incident light field using an optical system, and modulate it with a 2D pattern, creating a flat display which is view and illumination-dependent. It is free from electronic components. For distant light and a fixed observer position, we demonstrate a passive optical configuration which directly renders a 4D reflectance field in the real-world illumination behind it. We further propose an optical setup that allows for projecting out different angular distributions depending on the incident light direction. Combining multiple of these devices we build a display that renders a 6D experience, where the incident 2D illumination influences the outgoing light field, both in the spatial and in the angular domain. Possible applications of this technology are time-dependent displays driven by sunlight, object virtualization and programmable light benders / ray blockers without moving parts.

The quality of a 3D range scan should not depend on the surface properties of the object. Most active range scanning techniques, however, assume a diffuse reflector to allow for a robust detection of incident light patterns. In our approach we embed the object into a fluorescent liquid. By analyzing the light rays that become visible due to fluorescence rather than analyzing their reflections off the surface, we can detect the intersection points between the projected laser sheet and the object surface for a wide range of different materials. For transparent objects we can even directly depict a slice through the object in just one image by matching its refractive index to the one of the embedding liquid. This enables a direct sampling of the object geometry without the need for computational reconstruction. This way, a high-resolution 3D volume can be assembled simply by sweeping a laser plane through the object. We demonstrate the effectiveness of our light sheet range scanning approach on a set of objects manufactured from a variety of materials and material mixes, including dark, translucent and transparent objects.

Animated characters that move and gesticulate appropriately with spoken text are useful in a wide range of applications. Unfortunately, this class of movement is very difficult to generate, even more so when a unique, individual movement style is required. We present a system that, with a focus on arm gestures, is capable of producing full-body gesture animation for given input text in the style of a particular performer. Our process starts with video of a person whose gesturing style we wish to animate. A tool-assisted annotation process is performed on the video, from which a statistical model of the person's particular gesturing style is built. Using this model and input text tagged with theme, rheme and focus, our generation algorithm creates a gesture script. As opposed to isolated singleton gestures, our gesture script specifies a stream of continuous gestures coordinated with speech. This script is passed to an animation system, which enhances the gesture description with additional detail. It then generates either kinematic or physically simulated motion based on this description. The system is capable of generating gesture animations for novel text that are consistent with a given performer's style, as was successfully validated in an empirical user study.

We present a method for interactive computation of indirect illumination in large and fully dynamic scenes based on approximate visibility queries. While the high-frequency nature of direct lighting requires accurate visibility, indirect illumination mostly consists of smooth gradations, which tend to mask errors due to incorrect visibility. We exploit this by approximating visibility for indirect illumination with imperfect shadow maps ---low-resolution shadow maps rendered from a crude point-based representation of the scene. These are used in conjunction with a global illumination algorithm based on virtual point lights enabling indirect illumination of dynamic scenes at real-time frame rates. We demonstrate that imperfect shadow maps are a valid approximation to visibility, which makes the simulation of global illumination an order of magnitude faster than using accurate visibility.

We present a new approach for enhancing local scene contrast by unsharp masking over arbitrary surfaces under any form of illumination. Our adaptation of a well-known 2D technique to 3D interactive scenarios is designed to aid viewers in tasks like understanding complex or detailed geometric models, medical visualization and navigation in virtual environments. Our holistic approach enhances the depiction of various visual cues, including gradients from surface shading, surface reflectance, shadows, and highlights, to ease estimation of viewpoint, lighting conditions, shapes of objects and their world-space organization. Motivated by recent perceptual findings on 3D aspects of the Cornsweet illusion, we create scene coherent enhancements by treating cues in terms of their 3D context; doing so has a stronger effect than approaches that operate in a 2D image context and also achieves temporal coherence. We validate our unsharp masking in 3D with psychophysical experiments showing that the enhanced images are perceived to have better contrast and are preferred over unenhanced originals. Our operator runs at real-time rates on a GPU and the effect is easily controlled interactively within the rendering pipeline.

A semi-automatic approach is presented that enables the generation of a high-quality 3D model of a static object from an image sequence that was taken by a moving, uncalibrated consumer camera. A bounding box is placed around the object, and orthographic projections onto the sides of the bounding box are automatically generated out of the image sequence. These ortho-images can be imported as background maps in the orthographic views (e.g., the top, side, and front view) of any modeling package. Modelers can now use these ortho-images to guide their modeling by tracing the shape of the object over the ortho-images. This greatly improves the accuracy and efficiency of the manual modeling process. An additional advantage over existing semi-automatic systems is that modelers can use the modeling package that they are trained in and can thereby increase their productivity by applying the advanced modeling features the package offers. The results presented show that accurate 3D models can even be generated for translucent or specular surfaces, and the approach is therefore still applicable in cases where today's fully automatic image-based approaches or laser scanners would fail.

Smoke rendering is a standard technique for flow visualization. Most approaches are based on a volumetric, particle based, or image based representation of the smoke. This paper introduces an alternative representation of smoke structures: as semi-transparent streak surfaces. In order to make streak surface integration fast enough for interactive applications, we avoid expensive adaptive retriangulations by coupling the opacity of the triangles to their shapes. This way, the surface shows a smoke-like look even in rather turbulent areas. Furthermore, we show modifications of the approach to mimic smoke nozzles, wool tufts, and time surfaces. The technique is applied to a number of test data sets.

Diffusion weighted magnetic resonance imaging is a unique tool for non-invasive investigation of major nerve fiber tracts. Since the popular diffusion tensor (DT-MRI) model is limited to voxels with a single fiber direction, a number of high angular resolution techniques have been proposed to provide information about more diverse fiber distributions. Two such approaches are Q-Ball imaging and spherical deconvolution, which produce orientation distribution functions (ODFs) on the sphere. For analysis and visualization, the maxima of these functions have been used as principal directions, even though the results are known to be biased in case of crossing fiber tracts. In this paper, we present a more reliable technique for extracting discrete orientations from continuous ODFs, which is based on decomposing their higher-order tensor representation into an isotropic component, several rank-1 terms, and a small residual. Comparing to ground truth in synthetic data shows that the novel method reduces bias and reliably reconstructs crossing fibers which are not resolved as individual maxima in the ODF. We present results on both Q-Ball and spherical deconvolution data and demonstrate that the estimated directions allow for plausible fiber tracking in a real data set.

We present a novel algorithm to jointly capture the motion and the dynamic shape of humans from multiple video streams without using optical markers. Instead of relying on kinematic skeletons, as traditional motion capture methods, our approach uses a deformable high-quality mesh of a human as scene representation. It jointly uses an image-based 3D correspondence estimation algorithm and a fast Laplacian mesh deformation scheme to capture both motion and surface deformation of the actor from the input video footage. As opposed to many related methods, our algorithm can track people wearing wide apparel, it can straightforwardly be applied to any type of subject, e.g. animals, and it preserves the connectivity of the mesh over time. We demonstrate the performance of our approach using synthetic and captured real-world video sequences and validate its accuracy by comparison to the ground truth.

Translucent objects pose a difficult problem for traditional structured light 3D scanning techniques. Subsurface scattering corrupts the range estimation in two ways: by drastically reducing the signal-to-noise ratio and by shifting the intensity peak beneath the surface to a point which does not coincide with the point of incidence. In this paper we analyze and compare two descattering methods in order to obtain reliable 3D coordinates for translucent objects. By using polarization-difference imaging, subsurface scattering can be filtered out because multiple scattering randomizes the polarization direction of light while the surface reflectance partially keeps the polarization direction of the illumination. The descattered reflectance can be used for reliable 3D reconstruction using traditional optical 3D scanning techniques, such as structured light. Phase-shifting is another effective descattering technique if the frequency of the projected pattern is sufficiently high. We demonstrate the performance of these two techniques and the combination of them on scanning real-world translucent objects.

This work proposes a way to use a-priori knowledge on motion dynamics for markerless human motion capture (MoCap). Specifically, we match tracked motion patterns to training patterns in order to predict states in successive frames. Thereby, modeling the motion by means of twists allows for a proper scaling of the prior. Consequently, there is no need for training data of different frame rates or velocities. Moreover, the method allows to combine very different motion patterns. Experiments in indoor and outdoor scenarios demonstrate the continuous tracking of familiar motion patterns in case of artificial frame drops or in situations insufficiently constrained by the image data.

This paper presents a top-down approach to 3D data analysis by fitting a morphable model to scans of faces. In a unified framework, the algorithm optimizes shape, texture, pose and illumination simultaneously. The algorithm can be used as a core component in face recognition from scans. In an analysis-by-synthesis approach, raw scans are transformed into a PCA-based representation that is robust with respect to changes in pose and illumination. Illumination conditions are estimated in an explicit simulation that involves specular and diffuse components. The algorithm inverts the effect of shading in order to obtain the diffuse reflectance in each point of the facial surface. Our results include illumination correction, surface completion and face recognition on the FRGC database of scans.

By jointly applying a model-based marker-less motion capture approach and multi-view texture generation 3D videos of human actors can be reconstructed from multi-view video streams. If the input data were recorded under calibrated lighting, the texture information can also be used to measure time-varying surface reflectance. This way, 3D videos can be realistically displayed under novel lighting conditions. Reflectance estimation is only feasible if the multi-view texture-to-surface registration is consistent over time. In this paper, we propose two image-based warping methods that compensate registration errors due to inaccurate model geometry and shifting of apparel over the body.

Vast majority of digital images and video material stored today can capture only a fraction of visual information visible to the human eye and does not offer sufficient quality to fully exploit capabilities of new display devices. High dynamic range (HDR) image and video formats encode the full visible range of luminance and color gamut, thus offering ultimate fidelity, limited only by the capabilities of the human eye and not by any existing technology. In this paper we demonstrate how existing image and video compression standards can be extended to encode HDR content efficiently. This is achieved by a custom color space for encoding HDR pixel values that is derived from the visual performance data. We also demonstrate how HDR image and video compression can be designed so that it is backward compatible with existing formats.

Rendering global illumination effects for dynamic scenes at interactive frame rates is a computationally challenging task. Much of the computation time needed is spent during visibility queries between individual scene elements, and it is almost illusive to update this information at realtime even for moderately complex scenes. In this paper, we propose a global illumination approach for dynamic scenes that runs at near-real-time frame rates on a single PC. Our method is inspired by the principles of hierarchical radiosity and tackles the visibility problem by implicitly evaluating mutual visibility while constructing a hierarchical link structure between scene elements. By means of the same efficient and easy-to-implement framework, we are able to reproduce a large variety of complex lighting effects for moderately sized scenes, such as interreflections, environment map lighting as well as area light sources.

Vector field based shape deformations (VFSD) have been introduced as an efficient method to deform shapes in a volume-preserving foldover-free manner. However, mainly simple implicitly defined shapes like spheres or cylinders have been explored as deformation tools by now. In contrast, boundary constraint modeling approaches enable the user to exactly define the support of the deformation on the surface. We present an approach to explicitly control VFSD: a scalar function together with two thresholds is placed directly on the shape to mark regions of full, zero, and blended deformation. The resulting deformation is volume-preserving and free of local self-intersections. In addition, the full deformation is steered by a 3D parametric curve and a parametric twisting function. This way our deformations appear to be a generalization of the boundary constraint modeling metaphor. We apply our approach in different scenarios. A parallelization of the computation on the GPU allows for editing high-resolution meshes at interactive speed.

Standard density estimation approaches suffer from visible bias due to low-pass filtering of the lighting function. Therefore, most photon density estimation methods have been used primarily with inefficient Monte Carlo final gathering to achieve high-quality results for the indirect illumination. We present a density estimation technique for efficiently computing all-frequency global illumination in diffuse and moderately glossy scenes. In particular, we compute the direct, indirect, and caustics illumination during photon tracing from the light sources. Since the high frequencies in the illumination often arise from visibility changes and surface normal variations, we consider a kernel that takes these factors into account. To efficiently detect visibility changes, we introduce a hierarchical voxel data structure of the scene geometry, which is generated on GPU. Further, we preserve the surface orientation by computing the density estimation in ray space.

Both High Dynamic Range images and their tone mapped correspondents contain relative luminance values which have to be mapped on a scale of available gray levels of a display. Such mapping includes brightness adjustment, which has a direct impact on the final image appearance and the observers' assessment of image quality. We conduct a psychophysical experiment in which subjects adjust image brightness to match their preference. We observe that the brightness choice is consistent across subjects and is primarily affected by image content. We investigate popular methods for automatic brightness adjustment and show a significant inaccuracy for a group of images. The incorrect brightness adjustment degrades in these cases perceived image quality. We identify characteristics of images that are highly correlated with the subjects' choice of brightness and develop an improved model for the brightness adjustment.

A new geometry-based finite difference method for a fast and reliable detection of perceptually salient curvature extrema on surfaces approximated by dense triangle meshes is proposed. The foundations of the method are two simple curvature and curvature derivative formulas overlooked in modern differential geometry textbooks and seemingly new observation about inversion-invariant local surface-based differential forms.

We present a new method for noise removal on static and time-varying range data. Our approach predicts the restored position of a perturbed vertex using similar vertices in its neighborhood. It defines the required similarity measure in a new non-local fashion which compares regions of the surface instead of point pairs. This allows our algorithm to obtain a more accurate denoising result than previous state-of-the-art approaches and, at the same time, to better preserve fine features of the surface. Furthermore, our approach is easy to implement, effective, and flexibly applicable to different types of scanned data. We demonstrate this on several static and interesting new time-varying datasets obtained using laser and structured light scanners.

As large shape repositories become more common, the problem of automatically generating good views of shapes has recently gained prominence. However, very few of the proposed methods take into account the orientation of the shape in the resulting view, and none presents a satisfactory solution. In this paper, we present a simple, example based method to correct the orientation of a shape in a query image. Our method depends on the availability of a database of classified images containing correctly oriented shapes. In the first step, a candidate class for the query shape is identified, and in the second, the query shape is aligned with a target shape from the candidate class.

In this paper, we introduce and study a new problem of converting a given 3D shape (or a 2.5D range data) into a bas-relief. The problem can be considered as a geometry counterpart of the HDR image compression problem widely studied in computer graphics. In our approach to the shape bas-reliefing problem, we combine the concepts of mesh saliency, shape exaggerating, and discrete differential coordinates. The final bas-relief has a small width, preserves salient features of the original 3D shape, and, therefore, can be used for shape decorating purposes.

While isosurfaces of anisotropy measures for data from diffusion tensor magnetic resonance imaging (DT-MRI) are known to depict major anatomical structures, the anisotropy metric reduces the rich tensor data to a simple scalar field. In this work, we suggest that the part of the data which has been ignored by the metric can be used to segment anisotropy isosurfaces into anatomically meaningful regions. For the implementation, we propose an edge-based watershed method that adapts and extends a method from curvature-based mesh segmentation [MW99]. Finally, we use the segmentation results to enhance visualization of the data.

We present a simple and efficient approach to turn laser-scanned human geometry into a realistically moving virtual avatar. Instead of relying on the classical skeleton-based animation pipeline, our method uses a mesh-based Laplacian editing scheme to drive the motion of the scanned model. Our framework elegantly solves the motion retargeting problem and produces realistic non-rigid surface deformation with minimal user interaction. Realistic animations can easily be generated from a variety of input motion descriptions, which we exemplify by applying our method to both marker-free and marker-based motion capture data

Abstract Captured reflectance fields tend to provide a relatively coarse sampling of the incident light directions. As a result, sharp illumination features, such as highlights or shadow boundaries, are poorly reconstructed during relighting; highlights are disconnected, and shadows show banding artefacts. In this paper, we propose a novel interpolation technique for 4D reflectance fields that reconstructs plausible images even for non‐observed light directions. Given a sparsely sampled reflectance field, we can effectively synthesize images as they would have been obtained from denser sampling. The processing pipeline consists of three steps: (1) segmentation of regions where intermediate lighting cannot be obtained by blending, (2) appropriate flow algorithms for highlights and shadows, plus (3) a final reconstruction technique that uses image‐based priors to faithfully correct errors that might be introduced by the segmentation or flow step. The algorithm reliably reproduces scenes that contain specular highlights, interreflections, shadows or caustics.

Abstract We present a novel framework for efficiently computing the indirect illumination in diffuse and moderately glossy scenes using density estimation techniques. Many existing global illumination approaches either quickly compute an overly approximate solution or perform an orders of magnitude slower computation to obtain high‐quality results for the indirect illumination. The proposed method improves photon density estimation and leads to significantly better visual quality in particular for complex geometry, while only slightly increasing the computation time. We perform direct splatting of photon rays, which allows us to use simpler search data structures. Since our density estimation is carried out in ray space rather than on surfaces, as in the commonly used photon mapping algorithm, the results are more robust against geometrically incurred sources of bias. This holds also in combination with final gathering where photon mapping often overestimates the illumination near concave geometric features. In addition, we show that our photon splatting technique can be extended to handle moderately glossy surfaces and can be combined with traditional irradiance caching for sparse sampling and filtering in image space.

Abstract The ABSTRACT is to be in fully‐justified italicized text, between two horizontal lines, in one‐column format, below the author and affiliation information. Use the word “Abstract” as the title, in 9‐point Times, boldface type, left‐aligned to the text, initially capitalized. The abstract is to be in 9‐point, single‐spaced type. The abstract may be up to 3 inches (7.62 cm) long. Leave one blank line after the abstract, then add the subject categories according to the ACM Classification Index (see http://www.acm.org/class/1998/ ).

Abstract Performance has a spontaneity and “aliveness” that can be difficult to capture in more methodical animation processes such as keyframing. Access to performance animation has traditionally been limited to either low degree of freedom characters or required expensive hardware. We present a performance‐based animation system for humanoid characters that requires no special hardware, relying only on mouse and keyboard input. We deal with the problem of controlling such a high degree of freedom model with low degree of freedom input through the use of correlation maps which employ 2D mouse input to modify a set of expressively relevant character parameters. Control can be continuously varied by rapidly switching between these maps. We present flexible techniques for varying and combining these maps and a simple process for defining them. The tool is highly configurable, presenting suitable defaults for novices and supporting a high degree of customization and control for experts. Animation can be recorded on a single pass, or multiple layers can be used to increase detail. Results from a user study indicate that novices are able to produce reasonable animations within their first hour of using the system. We also show more complicated results for walking and a standing character that gestures and dances.

Abstract Significant advances have been achieved for realtime ray tracing recently, but realtime performance for complex scenes still requires large computational resources not yet available from the CPUs in standard PCs. Incidentally, most of these PCs also contain modern GPUs that do offer much larger raw compute power. However, limitations in the programming and memory model have so far kept the performance of GPU ray tracers well below that of their CPU counterparts. In this paper we present a novel packet ray traversal implementation that completely eliminates the need for maintaining a stack during kd‐tree traversal and that reduces the number of traversal steps per ray. While CPUs benefit moderately from the stackless approach, it improves GPU performance significantly. We achieve a peak performance of over 16 million rays per second for reasonably complex scenes, including complex shading and secondary rays. Several examples show that with this new technique GPUs can actually outperform equivalent CPU based ray tracers.

Abstract Represented in a Morphable Model, 3D faces follow curved trajectories in face space as they age. We present a novel algorithm that computes the individual aging trajectories for given faces, based on a non‐linear function that assigns an age to each face vector. This function is learned from a database of 3D scans of teenagers and adults using support vector regression. To apply the aging prediction to images of faces, we reconstruct a 3D model from the input image, apply the aging transformation on both shape and texture, and then render the face back into the same image or into images of other individuals at the appropriate ages, for example images of older children. Among other applications, our system can help to find missing children.

Abstract In this paper, a new free‐form shape deformation approach is proposed. We combine a skeleton‐based mesh deformation technique with discrete differential coordinates in order to create natural‐looking global shape deformations. Given a triangle mesh, we first extract a skeletal mesh, a two‐sided Voronoibased approximation of the medial axis. Next the skeletal mesh is modified by free‐form deformations. Then a desired global shape deformation is obtained by reconstructing the shape corresponding to the deformed skeletal mesh. The reconstruction is based on using discrete differential coordinates. Our method preserves fine geometric details and original shape thickness because of using discrete differential coordinates and skeleton‐based deformations. We also develop a new mesh evolution technique which allow us to eliminate possible global and local self‐intersections of the deformed mesh while preserving fine geometric details. Finally, we present a multi‐resolution version of our approach in order to simplify and accelerate the deformation process. In addition, interesting links between the proposed free‐form shape deformation technique and classical and modern results in the differential geometry of sphere congruences are established and discussed.

Facial expression analogy provides computer animation professionals with a tool to map expressions of an arbitrary source face onto an arbitrary target face. In the recent past, several algorithms have been presented in the literature that aim at putting the expression analogy paradigm into practice. Some of these methods exclusively handle expression mapping between 3-D face models, while others enable the transfer of expressions between images of faces only. None of them, however, represents a more general framework that can be applied to either of these two face representations. In this paper, we describe a novel generic method for analogy-based facial animation that employs the same efficient framework to transfer facial expressions between arbitrary 3-D face models, as well as between images of performer's faces. We propose a novel geometry encoding for triangle meshes, vertex-tent-coordinates, that enables us to formulate expression transfer in the 2-D and the 3-D case as a solution to a simple system of linear equations. Our experiments show that our method outperforms many previous analogy-based animation approaches in terms of achieved animation quality, computation time and generality.

Image-based relighting achieves high quality in rendering, but it requires a large number of measurements of the reflectance field. This article discusses sampling techniques that improve on the trade-offs between measurement effort and reconstruction quality. Specifically, we (i) demonstrate that sampling with point lights and from a sparse set of incoming light directions creates artifacts which can be reduced significantly by employing extended light sources for sampling, (ii) propose a sampling algorithm which incrementally chooses light directions adapted to the properties of the reflectance field being measured, thus capturing significant features faster than fixed-pattern sampling, and (iii) combine reflectance fields from two different light domain resolutions. We present an automated measurement setup for well-defined angular distributions of the incident, indirect illumination. It is based on programmable spotlights with controlled aperture that illuminate the walls around the scene.

We present a new method for real-time rendering of sophisticated lighting effects in and around refractive objects. It enables us to realistically display refractive objects with complex material properties, such as arbitrarily varying refractive index, inhomogeneous attenuation, as well as spatially-varying anisotropic scattering and reflectance properties. User-controlled changes of lighting positions only require a few seconds of update time. Our method is based on a set of ordinary differential equations derived from the eikonal equation, the main postulate of geometric optics. This set of equations allows for fast casting of bent light rays with the complexity of a particle tracer. Based on this concept, we also propose an efficient light propagation technique using adaptive wavefront tracing. Efficient GPU implementations for our algorithmic concepts enable us to render a combination of visual effects that were previously not reproducible in real-time.

Topological methods give concise and expressive visual representations of flow fields. The present work suggests a comparable method for the visualization of human brain diffusion MRI data. We explore existing techniques for the topological analysis of generic tensor fields, but find them inappropriate for diffusion MRI data. Thus, we propose a novel approach that considers the asymptotic behavior of a probabilistic fiber tracking method and define analogs of the basic concepts of flow topology, like critical points, basins, and faces, with interpretations in terms of brain anatomy. The resulting features are fuzzy, reflecting the uncertainty inherent in any connectivity estimate from diffusion imaging. We describe an algorithm to extract the new type of features, demonstrate its robustness under noise, and present results for two regions in a diffusion MRI dataset to illustrate that the method allows a meaningful visual analysis of probabilistic fiber tracking results.

By means of passive optical motion capture, real people can be authentically animated and photo-realistically textured. To import real-world characters into virtual environments, however, surface reflectance properties must also be known. We describe a video-based modeling approach that captures human shape and motion as well as reflectance characteristics from a handful of synchronized video recordings. The presented method is able to recover spatially varying surface reflectance properties of clothes from multiview video footage. The resulting model description enables us to realistically reproduce the appearance of animated virtual actors under different lighting conditions, as well as to interchange surface attributes among different people, e.g., for virtual dressing. Our contribution can be used to create 3D renditions of real-world people under arbitrary novel lighting conditions on standard graphics hardware.

We describe a simple and robust method for surface mesostructure acquisition. Our method builds on the observation that specular reflection is a reliable visual cue for surface mesostructure perception. In contrast to most photometric stereo methods, which take specularities as outliers and discard them, we propose a progressive acquisition system that captures a dense specularity field as the only information for mesostructure reconstruction. Our method can efficiently recover surfaces with fine-scale geometric details from complex real-world objects with a wide variety of reflection properties, including translucent, low albedo, and highly specular objects. We show results for a variety of objects including human skin, dried apricot, orange, jelly candy, black leather and dark chocolate.

We develop spherical barycentric coordinates. Analogous to classical, planar barycentric coordinates that describe the positions of points in a plane with respect to the vertices of a given planar polygon, spherical barycentric coordinates describe the positions of points on a sphere with respect to the vertices of a given spherical polygon. In particular, we introduce spherical mean value coordinates that inherit many good properties of their planar counterparts. Furthermore, we present a construction that gives a simple and intuitive geometric interpretation for classical barycentric coordinates, like Wachspress coordinates, mean value coordinates, and discrete harmonic coordinates. One of the most interesting consequences is the possibility to construct mean value coordinates for arbitrary polygonal meshes. So far, this was only possible for triangular meshes. Furthermore, spherical barycentric coordinates can be used for all applications where only planar barycentric coordinates were available up to now. They include Bézier surfaces, parameterization, free-form deformations, and interpolation of rotations.

This paper proposes a general framework for overfitting control in surface reconstruction from noisy point data. The problem we deal with is how to create a model that will capture as much detail as possible and simultaneously avoid reproducing the noise of the input points. The proposed framework is based on extra-sample validation. It is fully automatic and can work in conjunction with any surface reconstruction algorithm. We test the framework with a Radial Basis Function algorithm, Multi-level Partition of Unity implicits, and the Power Crust algorithm.

We discuss a shape representation based on a set of disconnected (planar) polygons. The polygons are computed by creating a BSP that contains approximately linear surface patches in each cell. This is achieved by employing two heuristics for finding appropriate split planes in each cell. Leaf nodes in the BSP tree represent either polygonal surface approximations or empty (clip) cells rather than split planes. We show that the resulting set of disconnected primitives typically leads to a better two-sided Hausdorff error for a given number of primitives than meshes. The BSP cells can be coded with few bits and, consequently, the tree is a compact shape representation. The special properties of BSPs are very useful in applications that need to perform spatial queries on the primitives, such as for occlusion and view frustum culling, and proximity or collision tests

An approach to automatically select stable and salient representative views of a given 3D object is proposed. Initially, a set of viewpoints are uniformly sampled along the surface of a bounding sphere. The sampled viewpoints are connected to their closest points to form a spherical graph in which each edge is weighted by a similarity measure between the two views from its incident vertices. Partitions of similar views are obtained using a graph partitioning procedure and their "centroids" are considered to be their representative views. Finally, the views are ranked based on a saliency measure to form the object’s representative views. This leads to a compact, human-oriented 2D description of a 3D object, and as such, is useful both for traditional applications like presentation and analysis of 3D shapes, and for emerging ones like indexing and retrieval in large shape repositories.

In this paper, we propose a new and powerful shape denoising technique for processing surfaces approximated by triangle meshes and soups. Our approach is inspired by recent non-local image denoising schemes and naturally extends bilateral mesh smoothing methods. The main idea behind the approach is very simple. A new position of vertex P of a noisy mesh is obtained as a weighted mean of mesh vertices Q with nonlinear weights reflecting a similarity between local neighborhoods of P and Q. We demonstrate that our technique outperforms recent state-of-the-art smoothing methods. We also suggest a new scheme for comparing different mesh/soup denoising methods.

We present an efficient approach for solving the spherical parameterization problem. The essence of the approach is to look for a solution in the curvilinear coordinate system without requiring the additional spherical constraints usually needed in Cartesian formulations. This setup allows us to take full advantage of some existing techniques originally developed for planar parameterization. Our results substantiate the efficiency of the method and confirm its robustness. Meshes of non-trivial geometry with tens of thousands of triangles are processed in a few seconds, always yielding bijective maps. This computational achievement bridges a so far wide gap in performance between spherical and planar parameterization

This paper presents an approach to extracting a path line oriented topological segmentation for periodic 2D timedependent vector fields. Topological methods aiming in capturing the asymptotic behavior of path lines rarely exist because path lines are usually only defined over a fixed time-interval, making statements about their asymptotic behavior impossible. For the data class of periodic vector fields, this restriction does not apply any more. Our approach detects critical path lines as well as basins from which the path lines converge to the critical ones. We demonstrate our approach on a number of test data sets.

Abstract We present a novel approach to create plausible 3D face models from vague recollections or incomplete descriptions. This task plays an important role in police work, where composite facial images of suspects need to be created from vague descriptions given by the eyewitnesses of an incident. Our approach is based on a morphable model of 3D faces and takes into account correlations among facial features based on human anatomy and ethnicity. Using these correlations, unspecified parts of the target face are automatically completed to yield a coherent face model. The system uses a novel paradigm for navigating face space and provides high‐level control of facial attributes as well as the possibility to import facial features from a database. In addition, the user can specify a set of attribute constraints that are used to restrict the target face to a residual subspace. These constraints can also be enforced on the example faces in the database, bringing their appearance closer to the mental image of the user, and thus avoiding confusing exposure to entirely different faces. We also propose a novel approach for adapting the system to local populations based on additional image databases that are converted into our 3D representation by automated shape reconstruction. We demonstrate the applicability of our system in a simulated forensic scenario and compare our results with those obtained by a professional forensic artist using state‐of‐the‐art software for creating composite images in police work. Categories and Subject Descriptors (according to ACM CCS): I.3.6 [Computer Graphics]: Methodology and Techniques—Interaction techniques I.4.10 [Image Processing and Computer Vision]: Image Representation—Hierarchical, Multidimensional, Statistical J.m [Computer Applications]: Miscellaneous—Forensic Sciences

Abstract Though ray tracing has recently become interactive, its high precomputation time for building spatial indices usually limits its applications to walkthroughs of static scenes. This is a major limitation, as most applications demand support for dynamically animated models. In this paper, we present a new approach to ray trace a special but important class of dynamic scenes, namely models whose connectivity does not change over time and for which all possible poses are known in advance. We support these kinds of models by introducing two new concepts: motion decomposition, and fuzzy kd‐trees. We analyze the animation and break the model down into submeshes with similar motion. For each of these submeshes and for every time step, we calculate a best affine transformation through a least square approach. Any residual motion is then captured in a single "fuzzy kd‐tree" for the entire animation. Together, these techniques allow for ray tracing animations without rebuilding the spatial index structures for the submeshes, resulting in interactive frame rates of 5 to 15 fps even on a single CPU. Categories and Subject Descriptors (according to ACM CCS): I.3.7 [Computer Graphics]: Ray tracing I.3.6 [Methodology and Techniques]: Graphics data structures and data types

Abstract High Dynamic Range (HDR) images capture the full range of luminance present in real world scenes, and unlike Low Dynamic Range (LDR) images, can simultaneously contain detailed information in the deepest of shadows and the brightest of light sources. For display or aesthetic purposes, it is often necessary to perform tone mapping, which creates LDR depictions of HDR images at the cost of contrast information loss. The purpose of this work is two‐fold: to analyze a displayed LDR image against its original HDR counterpart in terms of perceived contrast distortion, and to enhance the LDR depiction with perceptually driven colour adjustments to restore the original HDR contrast information. For analysis, we present a novel algorithm for the characterization of tone mapping distortion in terms of observed loss of global contrast, and loss of contour and texture details. We classify existing tone mapping operators accordingly. We measure both distortions with perceptual metrics that enable the automatic and meaningful enhancement of LDR depictions. For image enhancement, we identify artistic and photographic colour techniques from which we derive adjustments that create contrast with colour. The enhanced LDR image is an improved depiction of the original HDR image with restored contrast information. Categories and Subject Descriptors (according to ACM CCS): I.3.3 [Computer Graphics]: Picture/Image Generation I.4.0 [Image Processing and Computer Vision]: GeneralImage processing software

Abstract In this paper we extract and visualize the topological skeleton of two‐parameter‐dependent vector fields. This kind of vector data depends on two parameter dimensions, for instance physical time and a scale parameter. We show that two important classes of local bifurcations – fold and Hopf bifurcations – build line structures for which we present an approach to extract them. Furthermore we show that new kinds of structurally stable local bifurcations exist for this data, namely fold‐fold and Hopf‐fold bifurcations. We present a complete classification of them. We apply our topological extraction method to analyze a number of two‐parameter‐dependent vector fields with different physical interpretations of the two additional dimensions. Categories and Subject Descriptors (according to ACM CCS): I.3.3 [Computer Graphics]: Line and Curve Generation I.3.3 [Computer Graphics]: Picture/Image Generation

Abstract We conduct a series of experiments to investigate the desired properties of a tone mapping operator (TMO) and to design such an operator based on subjective data. We propose a novel approach to the tone mapping problem, in which the tone mapping parameters are determined based on the data from subjective experiments, rather than an image processing algorithm or a visual model. To collect this data, a series of experiments are conducted in which the subjects adjust three generic TMO parameters: brightness, contrast and color saturation. In two experiments, the subjects are to find a) the most preferred image without a reference image (preference task) and b) the closest image to the real‐world scene which the subjects are confronted with (fidelity task). We analyze subjects’ choice of parameters to provide more intuitive control over the parameters of a tone mapping operator. Unlike most of the researched TMOs that focus on rendering for standard low dynamic range monitors, we consider a broad range of potential displays, each offering different dynamic range and brightness. We simulate capabilities of such displays on a high dynamic range (HDR) display. This allows us to address the question of how tone mapping needs to be adjusted to accommodate displays with drastically different dynamic ranges. Categories and Subject Descriptors (according to ACM CCS): I.3.8 [Computer Graphics]: High dynamic range images, Visual perception, Tone mapping

We present an approach to define shape deformations by constructing and interactively modifying C 1 continuous time-dependent divergence-free vector fields. The deformation is obtained by a path line integration of the mesh vertices. This way, the deformation is volume-preserving, free of (local and global) self-intersections, feature preserving, smoothness preserving, and local. Different modeling metaphors support the approach which is able to modify the vector field on-the-fly according to the user input. The approach works at interactive frame rates for moderate mesh sizes, and the numerical integration preserves the volume with a high accuracy.

To embrace the imminent transition from traditional low-contrast video (LDR) content to superior high dynamic range (HDR) content, we propose a novel backward compatible HDR video compression (HDR MPEG) method. We introduce a compact reconstruction function that is used to decompose an HDR video stream into a residual stream and a standard LDR stream, which can be played on existing MPEG decoders, such as DVD players. The reconstruction function is finely tuned to the content of each HDR frame to achieve strong decorrelation between the LDR and residual streams, which minimizes the amount of redundant information. The size of the residual stream is further reduced by removing invisible details prior to compression using our HDR-enabled filter, which models luminance adaptation, contrast sensitivity, and visual masking based on the HDR content. Designed especially for DVD movie distribution, our HDR MPEG compression method features low storage requirements for HDR content resulting in a 30% size increase to an LDR video sequence. The proposed compression method does not impose restrictions or modify the appearance of the LDR or HDR video. This is important for backward compatibility of the LDR stream with current DVD appearance, and also enables independent fine tuning, tone mapping, and color grading of both streams.

We present an approach to visualizing correlations in 3D multifield scalar data. The core of our approach is the computation of correlation fields, which are scalar fields containing the local correlations of subsets of the multiple fields. While the visualization of the correlation fields can be done using standard 3D volume visualization techniques, their huge number makes selection and handling a challenge. We introduce the Multifield-Graph to give an overview of which multiple fields correlate and to show the strength of their correlation. This information guides the selection of informative correlation fields for visualization. We use our approach to visually analyze a number of real and synthetic multifield datasets.

We present an interactive system for fully dynamic scene lighting using captured high dynamic range (HDR) video environment maps. The key component of our system is an algorithm for efficient decomposition of HDR video environment map captured over hemisphere into a set of representative directional light sources, which can be used for the direct lighting computation with shadows using graphics hardware. The resulting lights exhibit good temporal coherence and their number can be adaptively changed to keep a constant framerate while good spatial distribution (stratification) properties are maintained. We can handle a large number of light sources with shadows using a novel technique which reduces the cost of BRDF-based shading and visibility computations. We demonstrate the use of our system in a mixed reality application in which real and synthetic objects are illuminated by consistent lighting at interactive framerates.

In the last decade, surface mesh parameterization has emerged as a standard technique in computer graphics. The ever increasing need for processing large and highly detailed data sets fosters the development of efficient parameterization techniques that can capture the geometry of the input meshes and produce low distortion planar maps. We present a set of novel techniques allowing for low distortion parameterization. In particular, we address one of the major shortcomings of linear methods by allowing the parametric representation to evolve freely on the plane without any fixed boundary vertices. Our method consists of several simple steps, each solving a linear problem. Our results exhibit a fair balance between high-quality and computational efficiency.

In this paper, we propose a new method for approximating an unorganized set of points scattered over a piecewise smooth surface by a triangle mesh. The method is based on the Garland-Heckbert local quadric error minimization strategy. First an adaptive spherical cover and auxiliary points corresponding to the cover elements are generated. Then the intersections between the spheres of the cover are analyzed and the auxiliary points are connected. Finally the resulting mesh is cleaned from non-manifold parts. The method allows us to control the approximation accuracy, process noisy data, and reconstruct sharp edges and corners. Further, the vast majority of the triangles of the generated mesh have their aspect ratios close to optimal. Thus our approach integrates the mesh reconstruction, smoothing, decimation, feature restoration, and remeshing stages together.

We propose a fast and robust method for detecting crest lines on surfaces approximated by dense triangle meshes. The crest lines, salient surface features defined via first- and second-order curvature derivatives, are widely used for shape matching and interrogation purposes. Their practical extraction is difficult because it requires good estimation of high-order surface derivatives. Our approach to the crest line detection is based on estimating the curvature tensor and curvature derivatives via local polynomial fitting.Since the crest lines are not defined in the surface regions where the surface focal set (caustic) degenerates, we introduce a new thresholding scheme which exploits interesting relationships between curvature extrema, the so-called MVS functional of Moreton and Sequin, and Dupin cyclides,An application of the crest lines to adaptive mesh simplification is also considered.

Feature sensitive mesh segmentation is important for many computer graphics and geometric modeling applications. In this paper, we develop a mesh segmentation method, which is capable of producing high-quality shape partitioning. It respects fine shape features and works well on various types of shapes, including natural shapes and mechanical parts. The method combines a procedure for clustering mesh normals with a modification of the mesh clarification technique. For clustering of mesh normals, we adopt Mean Shift, a powerful general purpose technique for clustering scattered data. We demonstrate advantages of our method by comparing it with two state-of-the-art mesh segmentation techniques.

We introduce new linear operators for surface parameterization. Given an initial mapping from the parametric plane onto a surface mesh, we establish a secondary map from the plane onto itself that mimics the initial one. The resulting low-distortion parameterization is smooth as it stems from solving a quasi-harmonic equation. Our parameterization method is robust and independent of (the quality of) the initial map.

We develop the first approach Tor interactive volume visualization based on a sophisticated rendering method of shear-warp type, wavelet data encoding techniques, and a trivariate spline model, which has been introduced recently. As a first step of our algorithm, we apply standard wavelet expansions to represent and decimate the given gridded three-dimensional data. Based on this data encoding, we give a sophisticated version of the shear-warp based volume rendering method. Our new algorithm visits each voxel only once taking advantage of the particular data organization of octrees. In addition, the hierarchies of the data guide the local (re)construction of the quadratic super-spline models, which we apply as a pure visualization tool. The low total degree of the polynomial pieces allows to numerically approximate the volume rendering integral efficiently. Since the coefficients of the splines are almost immediately available from the given data, Bernstein-Bezier techniques can be fully employed in our algorithms. In this way, we demonstrate that these models can be successfully applied to full volume rendering of hierarchically organized data. Our computational results show that (even when hierarchical approximations are used) the new approach leads to almost artifact-free visualizations of high quality for complicated and noise-contaminated volume data sets, while the computational effort is considerable low, i.e. our current implementation yields 1-2 frames per second for parallel perspective rendering a 2563 volume data set (using simple opacity transfer functions) in a 5122 view-port.

Line primitives are a very powerful visual attribute used for scientific visualization and in particular for 3D vector-field visualization. We extend the basic line primitives with additional visual attributes including color, line width, texture and orientation. To implement the visual attributes we represent the stylized line primitives as generalized cylinders. One important contribution of our work is an efficient rendering algorithm for stylized lines, which is hybrid in the sense that it uses both CPU and GPU based rendering. We improve the depth perception with a shadow algorithm. We present several applications for the visualization with stylized lines among which are the visualizations of 3D vector fields and molecular structures.

We introduce an approach to tracking vortex core lines in time-dependent 3D flow fields which are defined by the parallel vectors approach. They build surface structures in the 4D space-time domain. To extract them, we introduce two 4D vector fields which act as feature flow fields, i.e., their integration gives the vortex core structures. As part of this approach, we extract and classify local bifurcations of vortex core lines in space-time. Based on a 4D stream surface integration, we provide an algorithm to extract the complete vortex core structure. We apply our technique to a number of test data sets.

This paper presents an approach to extracting and classifying higher order critical points of 3D vector fields. To do so, we place a closed convex surface s around the area of interest. Then we show that the complete 3D classification of a critical point into areas of different flow behavior is equivalent to extracting the topological skeleton of an appropriate 2D vector field on s, if each critical point is equipped with an additional bit of information. Out of this skeleton, we create an icon which replaces the complete topological structure inside s for the visualization. We apply our method to find a simplified visual representation of clusters of critical points, leading to expressive visualizations of topologically complex 3D vector fields.

In multi-user virtual environments real-world people interact via digital avatars. In order to make the step from the real world onto the virtual stage convincing the digital equivalent of the user has to be personalized. It should reflect the shape and proportions, the kinematic properties, as well as the textural appearance of its real-world equivalent. In this paper, we present a novel spatio-temporal approach to create a personalized avatar from multi-view video data of a moving person. The avatar's geometry is generated by shape-adapting a template human body model. Its surface texture is assembled from multi-view video frames showing arbitrary different body poses. consistent surface texture for the model is generated using multi-view video frames from different camera views and different body poses. With our proposed method photo-realistic human avatars can be robustly generated.

We present a new algorithm for computing indirect illumination based on density estimation similarly to photon mapping. We accelerate the search for final gathering by reorganizing the computation in the reverse order. We use two trees that organize spatially not only the position of photons but also the position of final gather rays. The achieved speedup is algorithmic, the performance improvement takes advantage of logarithmic complexity of searching in trees. The algorithm requires almost no user settings unlike many known acceleration techniques for photon mapping. The image quality is the same as for traditional photon mapping with final gathering, since the algorithm does not approximate or interpolate. Optionally, the algorithm can be combined with other techniques such as density control and importance sampling. The algorithm creates a coherent access pattern to the main memory. This further improves on performance and also allows us to use efficient external data structures to alleviate the increased memory requirements.

An anchoring theory of lightness perception comprehensively explains many characteristics of human visual system such as lightness constancy and its spectacular failures which are important in the perception of images. We present a novel approach to tone mapping of high dynamic range (HDR) images which is inspired by the anchoring theory. The key concept of this method is the decomposition of an HDR image into areas (frameworks) of consistent luminance and the local calculation of the lightness values. The net lightness of an image is calculated via the merging of the frameworks proportionally to their strength. We stress out the importance of relating the luminance to a known brightness value (anchoring) and investigate the advantages of anchoring to the luminance value perceived as white. We validate the accuracy of the lightness reproduction in the presented algorithm by simulating a well known perception experiment. Our approach does not affect the local contrast and preserves the natural colors of an HDR image due to the linear handling of luminance.

Abstract A novel approach is presented to efficiently render local subsurface scattering effects. We introduce an importance sampling scheme for a practical subsurface scattering model. It leads to a simple and efficient rendering algorithm, which operates in image space, and which is even amenable for implementation on graphics hardware. We demonstrate the applicability of our technique to the problem of skin rendering, for which the subsurface transport of light typically remains local. Our implementation shows that plausible images can be rendered interactively using hardware acceleration.

We present an interactive method for applying deformations to a surface mesh while preserving its global shape and local properties. Two surface editing scenarios are discussed, which conceptually differ in the specification of deformations: Either interpolation constraints are imposed explicitly, e.g., by dragging a subset of vertices, or, deformation of a reference surface is mimicked. The contribution of this paper is a novel approach for interpolation of local deformations over the manifold and for efficiently establishing correspondence to a reference surface from only few pairs of markers. As a general tool for both scenarios, a harmonic field is constructed to guide the interpolation of constraints and to find correspondence required for deformation transfer. We show that our approach fits nicely in a unified mathematical framework, where the same type of linear operator is applied in all phases, and how this approach can be used to create an intuitive and interactive editing tool. Figure 1: A simple edit: The visualized harmonic field is used as guidance for bending the cactus (left). Here, the field is defined by one source (red) at the tip of the left arm and one sink (blue) below the middle of the trunk. The result is shown in the center image. Notice the different propagation of the rotation compared to the edit on the right, where three sources on all arms were chosen (without picture). 1.

We present a physically-based approach to compute the colors of the sky during the twilight period before sunrise and after sunset. The simulation is based on the theory of light scattering by small particles. A realistic atmosphere model is assumed, consisting of air molecules, aerosols, and water. Air density, aerosols, and relative humidity vary with altitude. In addition, the aerosol component varies in composition and particle-size distribution. This allows us to realistically simulate twilight phenomena for a wide range of different climate conditions. Besides considering multiple Rayleigh and Mie scattering, we take into account wavelength-dependent refraction of direct sunlight as well as the shadow of the Earth. Incorporating several optimizations into the radiative transfer simulation, a photo-realistic hemispherical twilight sky is computed in less than two hours on a conventional PC. The resulting radiometric data is useful, for instance, for high-dynamic range environment mapping, outdoor global illumination calculations, mesopic vision research and optical aerosol load probing.

In this paper, we present an image-based framework that acquires the reflectance properties of a human face. A range scan of the face is not required. Based on a morphable face model, the system estimates the 3D shape and establishes point-to-point correspondence across images taken from different viewpoints and across different individuals' faces. This provides a common parameterization of all reconstructed surfaces that can be used to compare and transfer BRDF data between different faces. Shape estimation from images compensates deformations of the face during the measurement process, such as facial expressions. In the common parameterization, regions of homogeneous materials on the face surface can be defined a priori. We apply analytical BRDF models to express the reflectance properties of each region and we estimate their parameters in a least-squares fit from the image data. For each of the surface points, the diffuse component of the BRDF is locally refined, which provides high detail. We present results for multiple analytical BRDF models, rendered at novel orientations and lighting conditions.

This paper describes approaches to topologically segmenting 2D time-dependent vector fields. For this class of vector fields, two important classes of lines exist: stream lines and path lines. Because of this, two segmentations are possible: either concerning the behavior of stream lines or of path lines. While topological features based on stream lines are well established, we introduce path line oriented topology as a new visualization approach in this paper. As a contribution to stream line oriented topology, we introduce new methods to detect global bifurcations like saddle connections and cyclic fold bifurcations as well as a method of tracking all isolated closed stream lines. To get the path line oriented topology, we segment the vector field into areas of attracting, repelling, and saddle-like behavior of the path lines. We compare both kinds of topologies and apply them to a number of test data sets.

The visualization of high-quality isosurfaces at interactive rates is an important tool in many simulation and visualization applications. Today, isosurfaces are most often visualized by extracting a polygonal approximation that is then rendered via graphics hardware or by using a special variant of preintegrated volume rendering. However, these approaches have a number of limitations in terms of the quality of the isosurface, lack of performance for complex data sets, or supported shading models. An alternative isosurface rendering method that does not suffer from these limitations is to directly ray trace the isosurface. However, this approach has been much too slow for interactive applications unless massively parallel shared-memory supercomputers have been used. In this paper, we implement interactive isosurface ray tracing on commodity desktop PCs by building on recent advances in real-time ray tracing of polygonal scenes and using those to improve isosurface ray tracing performance as well. The high performance and scalability of our approach will be demonstrated with several practical examples, including the visualization of highly complex isosurface data sets, the interactive rendering of hybrid polygonal/isosurface scenes, including high-quality ray traced shading effects, and even interactive global illumination on isosurfaces.

We present a hair model together with rendering algorithms suitable for real-time rendering. In our approach, we take into account the major lighting factors contributing to a realistic appearance of human hair: anisotropic reflection and self-shadowing. To deal with the geometric complexity of human hair, we combine single hair fibers into hair wisps, which are represented by textured triangle strips. Our rendering algorithms use OpenGL extensions to achieve real-time performance on recent commodity graphics boards. We demonstrate the applicability of our hair model for a variety of different hairstyles.

Efficient global illumination computation in dynamically changing environments is an important practical problem. In high-quality animation rendering costly "final gathering" technique is commonly used. We extend this technique into temporal domain by exploiting coherence between the subsequent frames. For this purpose we store previously computed incoming radiance samples and refresh them evenly in space and time using some aging criteria. The approach is based upon a two-pass photon mapping algorithm with irradiance cache, but it can be applied also in other gathering methods. The algorithm significantly reduces the cost of expensive indirect lighting computation and suppresses temporal aliasing with respect to the state of the art frame-by-frame rendering techniques

Photon tracing and density estimation are well established techniques in global illumination computation and rendering of high-quality animation sequences. Using traditional density estimation techniques it is difficult to remove stochastic noise inherent for photon-based methods while avoiding overblurring lighting details. In this paper we investigate the use of bilateral filtering for lighting reconstruction based on the local density of photon hit points. Bilateral filtering is applied in spatio-temporal domain and provides control over the level-of-details in reconstructed lighting. All changes of lighting below this level are treated as stochastic noise and are suppressed. Bilateral filtering proves to be efficient in preserving sharp features in lighting which is in particular important for high-quality caustic reconstruction. Also, flickering between subsequent animation frames is substantially reduced due to extending bilateral filtering into temporal domain.

We present a model-based approach to encode multiple synchronized video streams depicting a dynamic scene from different viewpoints. With approximate 3D scene geometry available, we compensate for motion as well as disparity by transforming all video images to object textures prior to compression. A two-level hierarchical coding strategy is employed to efficiently exploit inter-texture coherence as well as to ensure quick random access during decoding. Experimental validation shows that attainable compression ratios range up to 50:1 without subsampling. The proposed coding scheme is intended for use in conjunction with free-viewpoint video and 3D-TV applications.

We present a model-based approach to encode multiple synchronized video streams which show a dynamic scene from different viewpoints. By utilizing 3D scene geometry, we compensate for motion and disparity by transforming all video images to object textures prior to compression. A 4D SPIHT wavelet compression algorithm exploits interframe coherence in both temporal and spatial dimension. Unused texels increase the compression, and a shape mask can be omitted at the cost of higher decoder complexity. The proposed coding scheme is intended for use in conjunction with free-viewpoint video and 3D-TV applications.

In computer animation, human motion capture from video is a widely used technique to acquire motion parameters. The acquisition process typically requires an intrusion into the scene in the form of optical markers which are used to estimate the parameters of motion as well as the kinematic structure of the performer. Marker-free optical motion capture approaches exist, but due to their dependence on a specific type of a priori model they can hardly be used to track other subjects, e.g. animals. To bridge the gap between the generality of marker-based methods and the applicability of marker-free methods, we present a flexible non-intrusive approach that estimates both, a kinematic model and its parameters of motion from a sequence of voxel-volumes. The volume sequences are reconstructed from multi-view video data by means of a shape-from-silhouette technique. The described method is well-suited for but not limited to motion capture of human subjects.

Mesh partitioning and parts extraction have become key ingredients for many mesh manipulation applications both manual and automatic. In this paper, we present an intelligent scissoring operator for meshes which supports both automatic segmentation and manual cutting. Instead of segmenting the mesh by clustering, our approach concentrates on finding and defining the contours for cutting. This approach is based on the minima rule, which states that human perception usually divides a surface into parts along the contours of concave discontinuity of the tangent plane. The technique uses feature extraction to find such candidate feature contours. Subsequently, such a contour can be selected either automatically or manually, or the user may draw a 2D line to start the scissoring process. The given open contour is completed to form a loop around a specific part of the mesh, and this loop is used as the initial position of a 3D geometric snake. The snake moves by relaxation until it settles to define the final scissoring position. This process uses several fundamental geometric mesh attributes, such as curvature and centricity, and enables both automatic segmentation and an easy-to-use intelligent-scissoring operator.

We introduce a new technique for estimating the curvature tensor of a triangular mesh. The input of the algorithm is only a single triangle equipped with its (exact or estimated) vertex normals. This way we get a smooth junction of the curvature tensor inside each triangle of the mesh. We show that the error of the new method is comparable with the error of a cubic fitting approach if the incorporated normals are estimated. If the exact normals of the underlying surface are available at the vertices, the error drops significantly. We demonstrate the applicability of the new estimation at a rather complex data set.

We propose a polygonal decomposition of the 1-ring neighborhood of a quadrilateral mesh, which is suitable for the study of the Catmull-Clark subdivision scheme. The initial configuration consists of 2n planar 2n-gons and under the Catmull-Clark subdivision they transform into 4n planar n-gons coming in pairs of coplanar polygons and quadruples of parallel polygons. We calculate the eigenvalues and eigenvectors of the transformations of these configurations showing their relation with the tangent plane and the curvature properties of the subdivision surface. Using direct computations on circulant-block matrices, we show how the same eigenvalues can be analytically deduced from the subdivision matrix.

One of the main challenges in editing a mesh is to retain the visual appearance of the surface after applying various modifications. In this paper we advocate the use of linear differential coordinates as means to preserve the high-frequency detail of the surface. The differential coordinates represent the details and are defined by a linear transformation of the mesh vertices. This allows the reconstruction of the edited surface by solving a linear system that satisfies the reconstruction of the local details in least squares sense. Since the differential coordinates are defined in a global coordinate system they are not rotation-invariant. To compensate for that, we rotate them to agree with the rotation of an approximated local frame. We show that the linear least squares system can be solved fast enough to guarantee interactive response time thanks to a precomputed factorization of the coefficient matrix. We demonstrate that our approach enables to edit complex detailed meshes while keeping the shape of the details in their natural orientation.

We develop an adaptive RBF fitting procedure for a high quality approximation of a set of points scattered over a piecewise smooth surface. We use compactly supported RBFs whose centers are randomly chosen from the points. The randomness is controlled by the point density and surface geometry. For each RBF, its support size is chosen adoptively according to surface geometry at a vicinity of the RBF center. All these lead to a noise-robust high quality approximation of the set. We also adapt our basic technique for shape reconstruction from registered range scans by taking into account measurement confidences. Finally, an interesting link between our RBF fitting procedure and partition of unity approximations is established and discussed.

We propose a fast and simple method for generating a low-stretch mesh parameterization. Given a triangle mesh, we start from the floater shape preserving parameterization and then improve the parameterization gradually. At each improvement step, we optimize the parameterization generated at the previous step by minimizing a weighted quadratic energy where the weights are chosen in order to minimize the parameterization stretch. This optimization procedure does not generate triangle flips if the boundary of the parameter domain is a convex polygon. Moreover already the first optimization step produces a high-quality mesh parameterization. We compare our parameterization procedure with several state-of-the-art mesh parameterization methods and demonstrate its speed and high efficiency in parameterizing large and geometrically complex models.