Abstract Reflectance capture aims at the visual reproduction of an object under varying illumination. Past works differ substantially in their experimental overhead, from single‐ or few‐image approaches, that employ significant (often learned) priors at the expense of biased reconstructions, to more accurate approaches that tend to be time‐consuming, which to a good part is due to the need for carefully controlled illumination. Moreover, as we will show, the frequently employed point‐light or directional lighting tends to clip highlights and under‐sample the reflectance of glossy surfaces, leading to incorrect reconstructions under previously unseen illumination. Our work aims to strike a new balance, combining a low‐overhead capture methodology with a fast (neural) model fit. A key feature of our approach is the use of handheld, indirect bounce light that enables a convenient capture methodology, limits the dynamic range of the reflectance (effectively avoiding highlight clipping) and ensures contiguous hemispherical incidence, even with few images, eliminating under‐sampling of highly specular reflectance lobes. Moreover, our approach does not require training on pre‐existing material datasets and thus is not restricted by the choice of dataset, and its inference scales linearly with the number of pixels, scaling exceptionally well to large image sizes. As a result, our method enables high‐resolution capture of a spatially‐varying reflectance distribution function (SVBRDF) from a small set of casually captured, indirectly lit photographs, making high‐quality material acquisition practical even on consumer hardware. Overall, we believe that our method occupies a unique trade‐off between acquisition effort, model assumptions and resulting quality, and it has the potential to transform areas that routinely use handheld point‐light sources, such as the popular reflectance transformation imaging (RTI), leading to more faithful reproductions of artefacts and their surface characteristics.

Utilizing the complementary strengths of wavelength-specific range or depth sensors is crucial for robust computer-assisted tasks such as autonomous driving. Despite this, there is still little research done at the intersection of optical depth sensors and radars operating close range, where the target is decimeters away from the sensors. Together with a growing interest in high-resolution imaging radars operating in the near field, the question arises how these sensors behave in comparison to their traditional optical counterparts. In this work, we take on the unique challenge of jointly characterizing depth imagers from both, the optical and radio-frequency domain using a multimodal spatial calibration. We collect data from four depth imagers, with three optical sensors of varying operation principle and an imaging radar. We provide a comprehensive evaluation of their depth measurements with respect to distinct object materials, geometries, and object-to-sensor distances. Specifically, we reveal scattering effects of partially transmissive materials and investigate the response of radio-frequency signals. All object measurements are made public in form of a multimodal dataset, called MAROON, which can be accessed at: https://vwirth.github.io/maroon .

We introduce FruitNeRF++, a novel fruit-counting approach that combines contrastive learning with neural radiance fields to count fruits from unstructured input photographs of orchards. Our work is based on FruitNeRF [6], which employs a neural semantic field combined with a fruit-specific clustering approach. The requirement for adaptation for each fruit type limits the applicability of the method, and makes it difficult to use in practice. To lift this limitation, we design a shape-agnostic multi-fruit counting framework, that complements the RGB and semantic data with instance masks predicted by a vision foundation model. The masks are used to encode the identity of each fruit as instance embeddings into a neural instance field. By volumetrically sampling the neural fields, we extract a point cloud embedded with the instance features, which can be clustered in a fruit-agnostic manner to obtain the fruit count. We evaluate our approach using a synthetic dataset containing apples, plums, lemons, pears, peaches, and mangoes, as well as a real-world benchmark apple dataset. Our results demonstrate that FruitNeRF++ is easier to control and compares favorably to other state-of-the-art methods.

Rendering novel, relit views of a human head, given a monocular portrait image as input, is an inherently underconstrained problem. The traditional graphics solution is to explicitly decompose the input image into geometry, material and lighting via differentiable rendering; but this is constrained by the multiple assumptions and approximations of the underlying models and parameterizations of these scene components. We propose 3DPR, an image-based relighting model that leverages generative priors learnt from multi-view One-Light-at-A-Time (OLAT) images captured in a light stage. We introduce a new diverse and large-scale multi-view 4K OLAT dataset of 139 subjects to learn a high-quality prior over the distribution of high-frequency face reflectance. We leverage the latent space of a pre-trained generative head model that provides a rich prior over face geometry learnt from in-the-wild image datasets. The input portrait is first embedded in the latent manifold of such a model through an encoder-based inversion process. Then a novel triplane-based reflectance network trained on our lightstage data is used to synthesize high-fidelity OLAT images to enable image-based relighting. Our reflectance network operates in the latent space of the generative head model, crucially enabling a relatively small number of lightstage images to train the reflectance model. Combining the generated OLATs according to a given HDRI environment maps yields physically accurate environmental relighting results. Through quantitative and qualitative evaluations, we demonstrate that 3DPR outperforms previous methods, particularly in preserving identity and in capturing lighting effects such as specularities, self-shadows, and subsurface scattering.

Abstract 3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real‐time exploration of scenes. In these applications, coherence across camera frames and multiple views is crucial, be it for robust convergence of a scene reconstruction or for artifact‐free fly‐throughs. Recent work started mitigating artifacts that break multi‐view coherence, including popping artifacts due to inconsistent transparency sorting and perspective‐correct outlines of (2D) splats. At the same time, real‐time requirements forced such implementations to accept compromises in how transparency of large assemblies of 3D Gaussians is resolved, in turn breaking coherence in other ways. In our work, we aim at achieving maximum coherence, by rendering fully perspective‐correct 3D Gaussians while using a high‐quality approximation of accurate blending, hybrid transparency, on a per‐pixel level, in order to retain real‐time frame rates. Our fast and perspectively accurate approach for evaluation of 3D Gaussians does not require matrix inversions, thereby ensuring numerical stability and eliminating the need for special handling of degenerate splats, and the hybrid transparency formulation for blending maintains similar quality as fully resolved per‐pixel transparencies at a fraction of the rendering costs. We further show that each of these two components can be independently integrated into Gaussian splatting systems. In combination, they achieve up to 2× higher frame rates, 2× faster optimization, and equal or better image quality with fewer rendering artifacts compared to traditional 3DGS on common benchmarks.

In this work, we propose a system that covers the complete workflow for achieving controlled authoring and editing of textures that present distinctive local characteristics. These include various effects that change the surface appearance of materials, such as stains, tears, holes, abrasions, discoloration, and more. Such alterations are ubiquitous in nature, and including them in the synthesis process is crucial for generating realistic textures. We introduce a novel approach for creating textures with such blemishes, adopting a learning-based approach that leverages unlabeled examples. Our approach does not require manual annotations by the user; instead, it detects the appearance-altering features through unsupervised anomaly detection. The various textural features are then automatically clustered into semantically coherent groups, which are used to guide the conditional generation of images. Our pipeline as a whole goes from a small image collection to a versatile generative model that enables the user to interactively create and paint features on textures of arbitrary size. Notably, the algorithms we introduce for diffusion-based editing and infinite stationary texture generation are generic and should prove useful in other contexts as well. Project page: reality.tf.fau.de/pub/ardelean2025examplebased.html

Despite an emerging interest in MIMO radar, the utilization of its complementary strengths in combination with optical depth sensors has so far been limited to far-field applications, due to the challenges that arise from mutual sensor calibration in the near field. In fact, most related approaches in the autonomous industry propose target-based calibration methods using corner reflectors that have proven to be unsuitable for the near field. In contrast, we propose a novel, joint calibration approach for optical RGB-D sensors and MIMO radars that is designed to operate in the radar’s near-field range, within decimeters from the sensors. Our pipeline consists of a bespoke calibration target, allowing for automatic target detection and localization, followed by the spatial calibration of the two sensor coordinate systems through target registration. We validate our approach using two different depth sensing technologies from the optical domain. The experiments show the efficiency and accuracy of our calibration for various target displacements, as well as its robustness of our localization in terms of signal ambiguities.

We propose a novel method for Zero-Shot Anomaly Localization on textures. The task refers to identifying abnormal regions in an otherwise homogeneous image. To obtain a high-fidelity localization, we leverage a bijective mapping derived from the 1-dimensional Wasserstein Distance. As opposed to using holistic distances between distributions, the proposed approach allows pinpointing the non-conformity of a pixel in a local context with increased precision. By aggregating the contribution of the pixel to the errors of all nearby patches, we obtain a reliable anomaly score estimate. We validate our solution on several datasets and obtain more than a 40% reduction in error over the previous state of the art on the MVTec AD dataset in a zero-shot setting. Also see reality.tf.fau.de/pub/ardelean2024highfidelity.html.

Abstract Portrait viewpoint and illumination editing is an important problem with several applications in VR/AR, movies, and photography. Comprehensive knowledge of geometry and illumination is critical for obtaining photorealistic results. Current methods are unable to explicitly model in 3D while handling both viewpoint and illumination editing from a single image. In this paper, we propose VoRF, a novel approach that can take even a single portrait image as input and relight human heads under novel illuminations that can be viewed from arbitrary viewpoints. VoRF represents a human head as a continuous volumetric field and learns a prior model of human heads using a coordinate-based MLP with individual latent spaces for identity and illumination. The prior model is learned in an auto-decoder manner over a diverse class of head shapes and appearances, allowing VoRF to generalize to novel test identities from a single input image. Additionally, VoRF has a reflectance MLP that uses the intermediate features of the prior model for rendering One-Light-at-A-Time (OLAT) images under novel views. We synthesize novel illuminations by combining these OLAT images with target environment maps. Qualitative and quantitative evaluations demonstrate the effectiveness of VoRF for relighting and novel view synthesis, even when applied to unseen subjects under uncontrolled illumination. This work is an extension of Rao et al. (VoRF: Volumetric Relightable Faces 2022). We provide extensive evaluation and ablative studies of our model and also provide an application, where any face can be relighted using textual input.

Novel-view synthesis is an ill-posed problem in that it requires inference of previously unseen information. Recently, reviving the traditional field of image-based rendering, neural methods proved particularly suitable for this interpolation/extrapolation task; however, they often require a-priori scene-completeness or costly preprocessing steps and generally suffer from long (scene-specific) training times. Our work draws from recent progress in neural spatio-temporal supersampling to enhance a state-of-the-art neural renderer’s ability to infer novel-view information at inference time. We adapt a supersampling architecture [Xiao et al. 2020], which resamples previously rendered frames, to instead recombine nearby camera images in a multi-view dataset. These input frames are warped into a joint target frame, guided by the most recent (point-based) scene representation, followed by neural interpolation. The resulting architecture gains sufficient robustness to significantly improve transferability to previously unseen datasets. In particular, this enables novel applications for neural rendering where dynamically streamed content is directly incorporated in a (neural) image-based reconstruction of a scene. As we will show, our method reaches state-of-the-art performance when compared to previous works that rely on static and sufficiently densely sampled scenes; in addition, we demonstrate our system’s particular suitability for dynamically streamed content, where our approach is able to produce high-fidelity novel-view synthesis even with significantly fewer available frames than competing neural methods.

Computer-Generated Holography (CGH) offers the potential for genuine, high-quality three-dimensional visuals. However, fulfilling this potential remains a practical challenge due to computational complexity and visual quality issues. We propose a new CGH method that exploits gaze-contingency and perceptual graphics to accelerate the development of practical holographic display systems. Firstly, our method infers the user’s focal depth and generates images only at their focus plane without using any moving parts. Second, the images displayed are metamers; in the user’s peripheral vision, they need only be statistically correct and blend with the fovea seamlessly. Unlike previous methods, our method prioritises and improves foveal visual quality without causing perceptually visible distortions at the periphery. To enable our method, we introduce a novel metameric loss function that robustly compares the statistics of two given images for a known gaze location. In parallel, we implement a model representing the relation between holograms and their image reconstructions. We couple our differentiable loss function and model to metameric varifocal holograms using a stochastic gradient descent solver. We evaluate our method with an actual proof-of-concept holographic display, and we show that our CGH method leads to practical and perceptually three-dimensional image reconstructions.

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.

Abstract With the wider availability of full‐color 3D printers, color‐accurate 3D‐print preparation has received increased attention. A key challenge lies in the inherent translucency of commonly used print materials that blurs out details of the color texture. Previous work tries to compensate for these scattering effects through strategic assignment of colored primary materials to printer voxels. To date, the highest‐quality approach uses iterative optimization that relies on computationally expensive Monte Carlo light transport simulation to predict the surface appearance from subsurface scattering within a given print material distribution; that optimization, however, takes in the order of days on a single machine. In our work, we dramatically speed up the process by replacing the light transport simulation with a data‐driven approach. Leveraging a deep neural network to predict the scattering within a highly heterogeneous medium, our method performs around two orders of magnitude faster than Monte Carlo rendering while yielding optimization results of similar quality level. The network is based on an established method from atmospheric cloud rendering, adapted to our domain and extended by a physically motivated weight sharing scheme that substantially reduces the network size. We analyze its performance in an end‐to‐end print preparation pipeline and compare quality and runtime to alternative approaches, and demonstrate its generalization to unseen geometry and material values. This for the first time enables full heterogenous material optimization for 3D‐print preparation within time frames in the order of the actual printing time.

Abstract Controlled capture of real‐world material appearance yields tabulated sets of highly realistic reflectance data. In practice, however, its high memory footprint requires compressing into a representation that can be used efficiently in rendering while remaining faithful to the original. Previous works in appearance encoding often prioritized one of these requirements at the expense of the other, by either applying high‐fidelity array compression strategies not suited for efficient queries during rendering, or by fitting a compact analytic model that lacks expressiveness. We present a compact neural network‐based representation of BRDF data that combines high‐accuracy reconstruction with efficient practical rendering via built‐in interpolation of reflectance. We encode BRDFs as lightweight networks, and propose a training scheme with adaptive angular sampling, critical for the accurate reconstruction of specular highlights. Additionally, we propose a novel approach to make our representation amenable to importance sampling: rather than inverting the trained networks, we learn to encode them in a more compact embedding that can be mapped to parameters of an analytic BRDF for which importance sampling is known. We evaluate encoding results on isotropic and anisotropic BRDFs from multiple real‐world datasets, and importance sampling performance for isotropic BRDFs mapped to two different analytic models.

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.

We present a CNN-based method for outdoor highdynamic-range (HDR) environment map prediction from low-dynamic-range (LDR) portrait images. Our method relies on two different CNN architectures, one for light encoding and another for face-to-light prediction. Outdoor lighting is characterised by an extremely high dynamic range, and thus our encoding splits the environment map data between low and high-intensity components, and encodes them using tailored representations. The combination of both network architectures constitutes an end-to-end method for accurate HDR light prediction from faces at real-time rates, inaccessible for previous methods which focused on low dynamic range lighting or relied on non-linear optimisation schemes. We train our networks using both real and synthetic images, we compare our light encoding with other methods for light representation, and we analyse our results for light prediction on real images. We show that our predicted HDR environment maps can be used as accurate illumination sources for scene renderings, with potential applications in 3D object insertion for augmented reality.

Abstract This paper presents a novel technique for progressive online integration of uncalibrated image sequences with substantial geometric and/or photometric discrepancies into a single, geometrically and photometrically consistent image. Our approach can handle large sets of images, acquired from a nearly planar or infinitely distant scene at different resolutions in object domain and under variable local or global illumination conditions. It allows for efficient user guidance as its progressive nature provides a valid and consistent reconstruction at any moment during the online refinement process. Our approach avoids global optimization techniques, as commonly used in the field of image refinement, and progressively incorporates new imagery into a dynamically extendable and memory‐efficient Laplacian pyramid. Our image registration process includes a coarse homography and a local refinement stage using optical flow. Photometric consistency is achieved by retaining the photometric intensities given in a reference image, while it is being refined. Globally blurred imagery and local geometric inconsistencies due to, e.g. motion are detected and removed prior to image fusion. We demonstrate the quality and robustness of our approach using several image and video sequences, including handheld acquisition with mobile phones and zooming sequences with consumer cameras.

Abstract Realistic rendering using discrete reflectance measurements is challenging, because arbitrary directions on the light and view hemispheres are queried at render time, incurring large memory requirements and the need for interpolation. This explains the desire for compact and continuously parametrized models akin to analytic BRDFs; however, fitting BRDF parameters to complex data such as BTF texels can prove challenging, as models tend to describe restricted function spaces that cannot encompass real‐world behavior. Recent advances in this area have increasingly relied on neural representations that are trained to reproduce acquired reflectance data. The associated training process is extremely costly and must typically be repeated for each material. Inspired by autoencoders, we propose a unified network architecture that is trained on a variety of materials, and which projects reflectance measurements to a shared latent parameter space. Similarly to SVBRDF fitting, real‐world materials are represented by parameter maps, and the decoder network is analog to the analytic BRDF expression (also parametrized on light and view directions for practical rendering application). With this approach, encoding and decoding materials becomes a simple matter of evaluating the network. We train and validate on BTF datasets of the University of Bonn, but there are no prerequisites on either the number of angular reflectance samples, or the sample positions. Additionally, we show that the latent space is well‐behaved and can be sampled from, for applications such as mipmapping and texture synthesis.

Abstract Convolutional neural networks (CNNs) handle the case where filters extend beyond the image boundary using several heuristics, such as , or padding. These schemes are applied in an ad-hoc fashion and, being weakly related to the image content and oblivious of the target task, result in low output quality at the boundary. In this paper, we propose a simple and effective improvement that learns the boundary handling itself. At training-time, the network is provided with a separate set of boundary filters. At testing-time, we use these filters which have learned to extrapolate features at the boundary in an optimal way for the specific task. Our extensive evaluation, over a wide range of architectural changes (variations of layers, feature channels, or both), shows how the filters result in improved boundary handling. Furthermore, we investigate the efficacy of variations of such boundary filters with respect to convergence speed and accuracy. Finally, we demonstrate an improvement of 5–20% across the board of typical CNN applications (colorization, de-Bayering, optical flow, disparity estimation, and super-resolution). Supplementary material and code can be downloaded from the project page: http://geometry.cs.ucl.ac.uk/projects/2019/investigating-edge/ .

Abstract The Bidirectional Texture Function (BTF) is a data‐driven solution to render materials with complex appearance. A typical capture contains tens of thousands of images of a material sample under varying viewing and lighting conditions. While capable of faithfully recording complex light interactions in the material, the main drawback is the massive memory requirement, both for storing and rendering, making effective compression of BTF data a critical component in practical applications. Common compression schemes used in practice are based on matrix factorization techniques, which preserve the discrete format of the original dataset. While this approach generalizes well to different materials, rendering with the compressed dataset still relies on interpolating between the closest samples. Depending on the material and the angular resolution of the BTF, this can lead to blurring and ghosting artefacts. An alternative approach uses analytic model fitting to approximate the BTF data, using continuous functions that naturally interpolate well, but whose expressive range is often not wide enough to faithfully recreate materials with complex non‐local lighting effects (subsurface scattering, inter‐reflections, shadowing and masking…). In light of these observations, we propose a neural network‐based BTF representation inspired by autoencoders: our encoder compresses each texel to a small set of latent coefficients, while our decoder additionally takes in a light and view direction and outputs a single RGB vector at a time. This allows us to continuously query reflectance values in the light and view hemispheres, eliminating the need for linear interpolation between discrete samples. We train our architecture on fabric BTFs with a challenging appearance and compare to standard PCA as a baseline. We achieve competitive compression ratios and high‐quality interpolation/extrapolation without blurring or ghosting artifacts.

Commercially available full-color 3D printing allows for detailed control of material deposition in a volume, but an exact reproduction of a target surface appearance is hampered by the strong subsurface scattering that causes nontrivial volumetric cross-talk at the print surface. Previous work showed how an iterative optimization scheme based on accumulating absorptive materials at the surface can be used to find a volumetric distribution of print materials that closely approximates a given target appearance. In this work, we first revisit the assumption that pushing the absorptive materials to the surface results in minimal volumetric cross-talk. We design a full-fledged optimization on a small domain for this task and confirm this previously reported heuristic. Then, we extend the above approach that is critically limited to color reproduction on planar surfaces, to arbitrary 3D shapes. Our method enables high-fidelity color texture reproduction on 3D prints by effectively compensating for internal light scattering within arbitrarily shaped objects. In addition, we propose a content-aware gamut mapping that significantly improves color reproduction for the pathological case of thin geometric features. Using a wide range of sample objects with complex textures and geometries, we demonstrate color reproduction whose fidelity is superior to state-of-the-art drivers for color 3D printers.

Abstract Photographers routinely compose multiple manipulated photos of the same scene into a single image, producing a fidelity difficult to achieve using any individual photo. Alternately, 3D artists set up rendering systems to produce layered images to isolate individual aspects of the light transport, which are composed into the final result in post‐production. Regrettably, these approaches either take considerable time and effort to capture, or remain limited to synthetic scenes. In this paper, we suggest a method to decompose a single image into multiple layers that approximates effects such as shadow, diffuse illumination, albedo, and specular shading. To this end, we extend the idea of intrinsic images along two axes: first, by complementing shading and reflectance with specularity and occlusion, and second, by introducing directional dependence. We do so by training a convolutional neural network (CNN) with synthetic data. Such decompositions can then be manipulated in any off‐the‐shelf image manipulation software and composited back. We demonstrate the effectiveness of our decomposition on synthetic (i. e., rendered) and real data (i. e., photographs), and use them for photo manipulations, which are otherwise impossible to perform based on single images. We provide comparisons with state‐of‐the‐art methods and also evaluate the quality of our decompositions via a user study measuring the effectiveness of the resultant photo retouching setup. Supplementary material and code are available for research use at geometry.cs.ucl.ac.uk/projects/2017/layered-retouching .

Texture synthesis has grown into a mature field in computer graphics, allowing the synthesis of naturalistic textures and images from photographic exemplars. Surprisingly little work, however, has been dedicated to synthesizing tileable textures, that is, textures that when laid out in a regular grid of tiles form a homogeneous appearance suitable for use in memory-sensitive real-time graphics applications. One of the key challenges in doing so is that most natural input exemplars exhibit uneven spatial variations that, when tiled, show as repetitive patterns. We propose an approach to synthesize tileable textures while enforcing stationarity properties that effectively mask repetitions while maintaining the unique characteristics of the exemplar. We explore a number of alternative measures for texture stationarity and show how each measure can be integrated into a standard texture synthesis method (PatchMatch) to enforce stationarity at user-controlled scales. We demonstrate the efficacy of our approach using a database of 118 exemplar images, both from publicly available sources as well as new ones captured under uncontrolled conditions, and we quantitatively analyze alternative stationarity measures for their robustness across many test runs using different random seeds. In conclusion, we suggest a novel synthesis approach that employs local histogram matching to reliably turn input photographs of natural surfaces into tiles well suited for artifact-free tiling.

Interactive real-time scene acquisition from hand-held depth cameras has recently developed much momentum, enabling applications in ad-hoc object acquisition, augmented reality and other fields. A key challenge to online reconstruction remains error accumulation in the reconstructed camera trajectory, due to drift-inducing instabilities in the range scan alignments of the underlying iterative-closest-point (ICP) algorithm. Various strategies have been proposed to mitigate that drift, including SIFT-based pre-alignment, color-based weighting of ICP pairs, stronger weighting of edge features, and so on. In our work, we focus on surface curvature as a feature that is detectable on range scans alone and hence does not depend on accurate multi-sensor alignment. In contrast to previous work that took curvature into consideration, however, we treat curvature as an independent quantity that we consistently incorporate into every stage of the real-time reconstruction pipeline, including densely curvature-weighted ICP, range image fusion, local surface reconstruction, and rendering. Using multiple benchmark sequences, and in direct comparison to other state-of-the-art online acquisition systems, we show that our approach significantly reduces drift, both when analyzing individual pipeline stages in isolation, as well as seen across the online reconstruction pipeline as a whole.

Color texture reproduction in 3D printing commonly ignores volumetric light transport (cross-talk) between surface points on a 3D print. Such light diffusion leads to significant blur of details and color bleeding, and is particularly severe for highly translucent resin-based print materials. Given their widely varying scattering properties, this cross-talk between surface points strongly depends on the internal structure of the volume surrounding each surface point. Existing scattering-aware methods use simplified models for light difusion, and often accept the visual blur as an immutable property of the print medium. In contrast, our work counteracts heterogeneous scattering to obtain the impression of a crisp albedo texture on top of the 3D print, by optimizing for a fully volumetric material distribution that preserves the target appearance. Our method employs an efficient numerical optimizer on top of a general Monte-Carlo simulation of heterogeneous scattering, supported by a practical calibration procedure to obtain scattering parameters from a given set of printer materials. Despite the inherent translucency of the medium, we reproduce detailed surface textures on 3D prints. We evaluate our system using a commercial, five-tone 3D print process and compare against the printer's native color texturing mode, demonstrating that our method preserves high-frequency features well without having to compromise on color gamut.

Abstract We present a review of recent techniques for performing geometric analysis in cultural heritage (CH) applications. The survey is aimed at researchers in the areas of computer graphics, computer vision and CH computing, as well as to scholars and practitioners in the CH field. The problems considered include shape perception enhancement, restoration and preservation support, monitoring over time, object interpretation and collection analysis. All of these problems typically rely on an understanding of the structure of the shapes in question at both a local and global level. In this survey, we discuss the different problem forms and review the main solution methods, aided by classification criteria based on the geometric scale at which the analysis is performed and the cardinality of the relationships among object parts exploited during the analysis. We finalize the report by discussing open problems and future perspectives.

Material appearance acquisition usually makes a trade-off between acquisition effort and richness of reflectance representation. In this paper, we instead aim for both a light-weight acquisition procedure and a rich reflectance representation simultaneously, by restricting ourselves to one, but very important, class of appearance phenomena: texture-like materials. While such materials' reflectance is generally spatially varying, they exhibit self-similarity in the sense that for any point on the texture there exist many others with similar reflectance properties. We show that the texturedness assumption allows reflectance capture using only two images of a planar sample, taken with and without a headlight flash. Our reconstruction pipeline starts with redistributing reflectance observations across the image, followed by a regularized texture statistics transfer and a non-linear optimization to fit a spatially-varying BRDF (SVBRDF) to the resulting data. The final result describes the material as spatially-varying, diffuse and specular, anisotropic reflectance over a detailed normal map. We validate the method by side-by-side and novel-view comparisons to photographs, comparing normal map resolution to sub-micron ground truth scans, as well as simulated results. Our method is robust enough to use handheld, JPEG-compressed photographs taken with a mobile phone camera and built-in flash.

Abstract We present an interactive method to restore severely damaged historical parchments. When damaged by heat in a fire, such manuscripts undergo a complex deformation and contain various geometric distortions such as wrinkling, buckling, and shrinking, rendering them nearly illegible. They cannot be physically flattened due to the risk of further damage. We propose a virtual restoration framework to estimate the non‐rigid deformation the parchment underwent and to revert it, making reading the text significantly easier whilst maintaining the veracity of the textual content. We estimate the deformation by combining automatically extracted constraints with user‐provided hints informed by domain knowledge. We demonstrate that our method successfully flattens and straightens the text on a variety of pages scanned from a 17th century document which fell victim to fire damage.

Real-time or online 3D reconstruction has wide applicability and receives further interest due to availability of consumer depth cameras. Typical approaches use a moving sensor to accumulate depth measurements into a single model which is continuously refined. Designing such systems is an intricate balance between reconstruction quality, speed, spatial scale, and scene assumptions. Existing online methods either trade scale to achieve higher quality reconstructions of small objects/scenes. Or handle larger scenes by trading real-time performance and/or quality, or by limiting the bounds of the active reconstruction. Additionally, many systems assume a static scene, and cannot robustly handle scene motion or reconstructions that evolve to reflect scene changes. We address these limitations with a new system for real-time dense reconstruction with equivalent quality to existing online methods, but with support for additional spatial scale and robustness in dynamic scenes. Our system is designed around a simple and flat point-Based representation, which directly works with the input acquired from range/depth sensors, without the overhead of converting between representations. The use of points enables speed and memory efficiency, directly leveraging the standard graphics pipeline for all central operations, i.e., camera pose estimation, data association, outlier removal, fusion of depth maps into a single denoised model, and detection and update of dynamic objects. We conclude with qualitative and quantitative results that highlight robust tracking and high quality reconstructions of a diverse set of scenes at varying scales.

We present PanoInserts: a novel teleconferencing system that uses smartphone cameras to create a surround representation of meeting places. We take a static panoramic image of a location into which we insert live videos from smartphones. We use a combination of marker- and image-based tracking to position the video inserts within the panorama, and transmit this representation to a remote viewer. We conduct a user study comparing our system with fully-panoramic video and conventional webcam video conferencing for two spatial reasoning tasks. Results indicate that our system performs comparably with fully-panoramic video, and better than webcam video conferencing in tasks that require an accurate surrounding representation of the remote space. We discuss the representational properties and usability of varying video presentations, exploring how they are perceived and how they influence users when performing spatial reasoning tasks.

In the BEAMING project we have been extending the scope of collaborative mixed reality to include the representation of users in multiple modalities, including augmented reality, situated displays and robots. A single user (a visitor) uses a high-end virtual reality system (the transporter) to be virtually teleported to a real remote location (the destination). The visitor may be tracked in several ways including emotion and motion capture. We reconstruct the destination and the people within it (the locals). In achieving this scenario, BEAMING has integrated many heterogeneous systems. In this paper, we describe the design and key implementation choices in the Beaming Scene Service (BSS), which allows the various processes to coordinate their behaviour. The core of the system is a light-weight shared object repository that allows loose coupling between processes with very different requirements (e.g. embedded control systems through to mobile apps). The system was also extended to support the notion of presence awareness. We demonstrate two complex applications built with the BSS.

Abstract We present an interactive application for browsing severely damaged documents and other cultural artefacts. Such documents often contain strong geometric distortions such as wrinkling, buckling, and shrinking and cannot be flattened physically due to the high risk of causing further damage. Previous methods for virtual restoration involve globally flattening a 3D reconstruction of the document to produce a static image. We show how this global approach can fail in cases of severe geometric distortion, and instead propose an interactive viewer which allows a user to browse a document while dynamically flattening only the local region under inspection. Our application also records the provenance of the reconstruction by displaying the reconstruction side by side with the original image data.

Spatially-varying reflectance and small geometric variations play a vital role in the appearance of real-world surfaces. Consequently, robust, automatic capture of such models is highly desirable; however, current systems require either specialized hardware, long capture times, user intervention, or rely heavily on heuristics. We describe an acquisition setup that utilizes only portable commodity hardware (an LCD display, an SLR camera) and contains no moving parts. In particular, a laptop screen can be used for illumination. Our setup, aided by a carefully constructed image formation model, automatically produces realistic spatially-varying reflectance parameters over a wide range of materials from diffuse to almost mirror-like specular surfaces, while requiring relatively few photographs. We believe our system is the first to offer such generality, while requiring only standard office equipment and no user intervention or parameter tuning. Our results exhibit a good qualitative match to photographs taken under novel viewing and lighting conditions for a range of materials.

Additive manufacturing (3D printing) is commonly used to produce physical models for a wide variety of applications, from archaeology to design. While static models are directly supported, it is desirable to also be able to print models with functional articulations, such as a hand with joints and knuckles, without the need for manual assembly of joint components. Apart from having to address limitations inherent to the printing process, this poses a particular challenge for articulated models that should be posable: to allow the model to hold a pose, joints need to exhibit internal friction to withstand gravity, without their parts fusing during 3D printing. This has not been possible with previous printable joint designs. In this paper, we propose a method for converting 3D models into printable, functional, non-assembly models with internal friction. To this end, we have designed an intuitive work-flow that takes an appropriately rigged 3D model, automatically fits novel 3D-printable and posable joints, and provides an interface for specifying rotational constraints. We show a number of results for different articulated models, demonstrating the effectiveness of our method.

Time-of-Flight cameras provide high-frame-rate depth measurements within a limited range of distances. These readings can be extremely noisy and display unique errors, for instance, where scenes contain depth discontinuities or materials with low infrared reflectivity. Previous works have treated the amplitude of each Time-of-Flight sample as a measure of confidence. In this paper, we demonstrate the shortcomings of this common lone heuristic, and propose an improved per-pixel confidence measure using a Random Forest regressor trained with real-world data. Using an industrial laser scanner for ground truth acquisition, we evaluate our technique on data from two different Time-of-Flight cameras1. We argue that an improved confidence measure leads to superior reconstructions in subsequent steps of traditional scan processing pipelines. At the same time, data with confidence reduces the need for point cloud smoothing and median filtering.

Abstract We propose a novel system for designing and manufacturing surfaces that produce desired caustic images when illuminated by a light source. Our system is based on a nonnegative image decomposition using a set of possibly overlapping anisotropic Gaussian kernels. We utilize this decomposition to construct an array of continuous surface patches, each of which focuses light onto one of the Gaussian kernels, either through refraction or reflection. We show how to derive the shape of each continuous patch and arrange them by performing a discrete assignment of patches to kernels in the desired caustic. Our decomposition provides for high fidelity reconstruction of natural images using a small collection of patches. We demonstrate our approach on a wide variety of caustic images by manufacturing physical surfaces with a small number of patches.

Abstract The problem of noise in Monte‐Carlo rendering arising from estimator variance is well‐known and well‐studied. In this work, we concentrate on identifying individual light paths as outliers that lead to significant spikes of noise and represent a challenge for existing filtering methods. Most noise‐reduction methods, such as importance sampling and stratification, attempt to generate samples that are expected a priori to have lower variance, but do not take into account actual sample values. While these methods are essential to decrease overall noise, we show that filtering samples a posteriori allows for greater reduction of spiked noise. In particular, given evaluated sample values, outliers can be identified and removed. Conforming with conventions in statistics, we emphasize that the term “outlier” should not be taken as synonymous with “incorrect”, but as referring to samples that distort the empirically‐observed distribution of energy relative to the true underlying distribution. By expressing a path distribution in joint image and color space, we show how outliers can be characterized by their density across the set of all nearby paths in this space. We show that removing these outliers leads to significant improvements in rendering quality.

Abstract This paper presents a novel framework for elliptical weighted average (EWA) surface splatting with time‐varying scenes. We extend the theoretical basis of the original framework by replacing the 2D surface reconstruction filters by 3D kernels which unify the spatial and temporal component of moving objects. Based on the newly derived mathematical framework we introduce a rendering algorithm that supports the generation of high‐quality motion blur for point‐based objects using a piecewise linear approximation of the motion. The rendering algorithm applies ellipsoids as rendering primitives which are constructed by extending planar EWA surface splats into the temporal dimension along the instantaneous motion vector. Finally, we present an implementation of the proposed rendering algorithm with approximated occlusion handling using advanced features of modern GPUs and show its capability of producing motion‐blurred result images at interactive frame rates.

Facial appearance depends on both the physical and physiological state of the skin. As people move, talk, undergo stress, and change expression, skin appearance is in constant flux. One of the key indicators of these changes is thecolorof skin. Skin color is determined by scattering and absorption of light within the skin layers, caused mostly by concentrations of two chromophores, melanin and hemoglobin. In this paper we present a real-time dynamic appearance model of skin built fromin vivomeasurements of melanin and hemoglobin concentrations. We demonstrate an efficient implementation of our method, and show that it adds negligible overhead to existing animation and rendering pipelines. Additionally, we develop a realistic, intuitive, and automatic control for skin color, which we term askin appearance rig.This rig can easily be coupled with a traditional geometric facial animation rig. We demonstrate our method by augmenting digital facial performance with realistic appearance changes.

We present a multiple-feature approach for determining matches between small fragments of archaeological artifacts such as Bronze-Age and Roman frescoes. In contrast with traditional 2D and 3D shape matching approaches, we introduce a set of feature descriptors that are based on not only color and shape, but also normal maps. These are easy to acquire and combine high data quality with discriminability and robustness to some types of deterioration. Our feature descriptors range from general-purpose to domain-specific, and are quick to compute and match. We have tested our system on three datasets of fresco fragments, demonstrating that multi-cue matching using different subsets of features leads to different tradeoffs between efficiency and effectiveness. In particular, we show that normal-based features are more effective than color-based ones at similar computational complexity, and that 3D features are more discriminative than ones based on 2D or normals, but at higher computational cost. We also demonstrate how machine learning techniques can be used to effectively combine our new features with traditional ones. Our results show good retrieval performance, significantly improving upon the match prediction rate of state-of-the-art 3D matching algorithms, and are expected to extend to general matching problems in applications such as texture synthesis and forensics.

We develop a novel technique for authenticating physical documents by using random, naturally occurring imperfections in paper texture. To this end, we devised a new method for measuring the three-dimensional surface of a paper without modifying the document in any way, using only a commodity scanner. From this physical feature, we generate a concise fingerprint that uniquely identifies the document. Our method is secure against counterfeiting, robust to harsh handling, and applicable even before any content is printed on a page. It has a wide range of applications, including detecting forged currency and tickets, authenticating passports, and halting counterfeit goods. On a more sinister note, document identification could be used to de-anonymize printed surveys and to compromise the secrecy of paper ballots.

Display technology is advancing quickly with peak luminance increasing significantly, enabling high-dynamic-range displays. However, perceptual color appearance under extended luminance levels has not been studied, mainly due to the unavailability of psychophysical data. Therefore, we conduct a psychophysical study in order to acquire appearance data for many different luminance levels (up to 16,860 cd/m2) covering most of the dynamic range of the human visual system. These experimental data allow us to quantify human color perception under extended luminance levels, yielding a generalized color appearance model. Our proposed appearance model is efficient, accurate and invertible. It can be used to adapt the tone and color of images to different dynamic ranges for cross-media reproduction while maintaining appearance that is close to human perception.

We propose a system for manufacturing physical surfaces that, in aggregate, exhibit a desired surface appearance. Our system begins with a user specification of a BRDF, or simply a highlight shape, and infers the required distribution of surface slopes. We sample this distribution, optimize for a maximally-continuous and valley-minimizing height field, and finally mill the surface using a computer-controlled machine tool. We demonstrate a variety of surfaces, ranging from reproductions of measured BRDFs to materials with unconventional highlights.

In this work, we consider the dense reconstruction of specular objects. We propose the use of a specularity constraint, based on surface normal/depth consistency, to define a matching cost function that can drive standard stereo reconstruction methods. We discuss the types of ambiguity that can arise, and suggest an aggregation method based on anisotropic diffusion that is particularly suitable for this matching cost function. We also present a controlled illumination setup that includes a pair of cameras and one LCD monitor, which is used as a calibrated, variable-position light source. We use this setup to evaluate the proposed method on real data, and demonstrate its capacity to recover high-quality depth and orientation from specular objects.

Although mature technologies exist for acquiring images, geometry, and normals of small objects, they remain cumbersome and time-consuming for non-experts to employ on a large scale. In an archaeological setting, a practical acquisition system for routine use on every artifact and fragment would open new possibilities for archiving, analysis, and dissemination. We present an inexpensive system for acquiring all three types of information, and associated metadata, for small objects such as fragments of wall paintings. The acquisition system requires minimal supervision, so that a single, non-expert user can scan at least 10 fragments per hour. To achieve this performance, we introduce new algorithms to robustly and automatically align range scans, register 2-D scans to 3-D geometry, and compute normals from 2-D scans. As an illustrative application, we present a novel 3-D matching algorithm that efficiently searches for matching fragments using the scanned geometry.

We introduce a layered, heterogeneous spectral reflectance model for human skin. The model captures the inter-scattering of light among layers, each of which may have an independent set of spatially-varying absorption and scattering parameters. For greater physical accuracy and control, we introduce an infinitesimally thin absorbing layer between scattering layers. To obtain parameters for our model, we use a novel acquisition method that begins with multi-spectral photographs. By using an inverse rendering technique, along with known chromophore spectra, we optimize for the best set of parameters for each pixel of a patch. Our method finds close matches to a wide variety of inputs with low residual error. We apply our model to faithfully reproduce the complex variations in skin pigmentation. This is in contrast to most previous work, which assumes that skin is homogeneous or composed of homogeneous layers. We demonstrate the accuracy and flexibility of our model by creating complex skin visual effects such as veins, tattoos, rashes, and freckles, which would be difficult to author using only albedo textures at the skin's outer surface. Also, by varying the parameters to our model, we simulate effects from external forces, such as visible changes in blood flow within the skin due to external pressure.

We present a system for semi-automatic creation of bas-relief sculpture. As an artistic medium, relief spans the continuum between 2D drawing or painting and full 3D sculpture. Bas-relief (or low relief) presents the unique challenge of squeezing shapes into a nearly-flat surface while maintaining as much as possible the perception of the full 3D scene. Our solution to this problem adapts methods from the tone-mapping literature, which addresses the similar problem of squeezing a high dynamic range image into the (low) dynamic range available on typical display devices. However, the bas-relief medium imposes its own unique set of requirements, such as maintaining small, fixed-size depth discontinuities. Given a 3D model, camera, and a few parameters describing the relative attenuation of different frequencies in the shape, our system creates a relief that gives the illusion of the 3D shape from a given vantage point while conforming to a greatly compressed height.

We present a novel architecture for hardware-accelerated rendering of point primitives. Our pipeline implements a refined version of EWA splatting, a high quality method for antialiased rendering of point sampled representations. A central feature of our design is the seamless integration of the architecture into conventional, OpenGL-like graphics pipelines so as to complement triangle-based rendering. The specific properties of the EWA algorithm required a variety of novel design concepts including a ternary depth test and using an on-chip pipelined heap data structure for making the memory accesses of splat primitives more coherent. In addition, we developed a computationally stable evaluation scheme for perspectively corrected splats. We implemented our architecture both on reconfigurable FPGA boards and as an ASIC prototype, and we integrated it into an OpenGL-like software implementation. Our evaluation comprises a detailed performance analysis using scenes of varying complexity.

We have measured 3D face geometry, skin reflectance, and subsurface scattering using custom-built devices for 149 subjects of varying age, gender, and race. We developed a novel skin reflectance model whose parameters can be estimated from measurements. The model decomposes the large amount of measured skin data into a spatially-varying analytic BRDF, a diffuse albedo map, and diffuse subsurface scattering. Our model is intuitive, physically plausible, and -- since we do not use the original measured data -- easy to edit as well. High-quality renderings come close to reproducing real photographs. The analysis of the model parameters for our sample population reveals variations according to subject age, gender, skin type, and external factors (e.g., sweat, cold, or makeup). Using our statistics, a user can edit the overall appearance of a face (e.g., changing skin type and age) or change small-scale features using texture synthesis (e.g., adding moles and freckles). We are making the collected statistics publicly available to the research community for applications in face synthesis and analysis.

Animation of photorealistic computer graphics models is an important goal for many applications. Image-based modeling has emerged as a promising approach to capture and visualize real-world objects. Animating image-based models, however, is still a largely unsolved problem. In this paper, we extend a popular image-based representation called surface reflectance field to animate and render deformable real-world objects under arbitrary illumination. Deforming the surface reflectance field is achieved by modifying the underlying impostor geometry. We augment the impostor by a local parameterization that allows the correct evaluation of acquired reflectance images, preserving the original light model on the deformed surface. We present a deferred shading scheme to handle the increased amount of data involved in shading the deformable surface reflectance field. We show animations of various objects that were acquired with 3D photography.

We present a new scheme for digital watermarking of point-sampled geometry based on spectral analysis. By extending existing algorithms designed for polygonal data to unstructured point clouds, our method is particularly suited for scanned models, where the watermark can be directly embedded in the raw data obtained from the 3D acquisition device. To handle large data sets efficiently, we apply a fast hierarchical clustering algorithm that partitions the model into a set of patches. Each patch is mapped into the space of eigenfunctions of an approximate Laplacian operator to obtain a decomposition of the patch surface into discrete frequency bands. The watermark is then embedded into the low frequency components to minimize visual artifacts in the model geometry. During extraction, the target model is resampled at optimal resolution using an MLS projection. After extracting a watermark from this model, the corresponding bit stream is analyzed using statistical methods based on correlation. We have applied our method to a number of point-sampled models of different geometric and topological complexity. These experiments show that our watermarking scheme is robust against numerous attacks, including low-pass filtering, resampling, affine transformations, cropping, additive random noise, and combinations of the above.