Abstract We present the first motion generation system for playtesting virtual reality (VR) games. Our player model generates VR headset and handheld controller movements from in‐game object arrangements, guided by style reference gameplay examples. We train on the large BOXRR‐23 dataset and apply our framework on the popular VR game Beat Saber . The resulting model Robo‐Saber reproduces skilled performance and captures diverse player behaviors present in the training data. Robo‐Saber demonstrates promise in synthesizing rich gameplay data for predictive applications and enabling whole‐body physics‐based VR playtesting.

Abstract Recent machine learning methods have significantly advanced the state of the art in the classic problem of representing surface appearance over angle, space, and scale. The models tend, however, to be relatively heavy compared to traditional fixed‐function representations, making real‐time application challenging. We present a neural shading architecture that allows the use of smaller and faster‐to‐evaluate neural networks than current state of the art, while faithfully representing complex spatial and angular variation. We target the angular complexity that arises both from prefiltering normal‐mapped SVBRDFs, as well as complex, measured homogeneous BRDFs. A key architectural innovation is the introduction of a multiplicative interaction (“gating”) between learnable parameters that significantly increases our model's expressive power. Our straightforward, unop‐timized shader implementation renders over 1000 full HD frames per second on a consumer GPU using our default parameters.

Forecasting electroencephalography (EEG) signals, that is, estimating future values of the time series based on the past ones, is essential in many real-time EEG-based applications, such as brain-computer interfaces and closed-loop brain stimulation. As these applications are becoming more and more common, the importance of a good prediction model has increased. Previously, the autoregressive model (AR) has been employed for this task; however, its prediction accuracy tends to fade quickly as multiple steps are predicted. We aim to improve on this by applying probabilistic deep learning to make robust longer-range forecasts. For this, we applied the probabilistic deep neural network model WaveNet to forecast resting-state EEG in theta- (4-7.5 Hz) and alpha-frequency (8-13 Hz) bands and compared it to the AR model. WaveNet reliably predicted EEG signals in both theta and alpha frequencies 150 ms ahead, with mean absolute errors of 1.0 ± 1.1 µV (theta) and 0.9 ± 1.1 µV (alpha), and outperformed the AR model in estimating the signal amplitude and phase. Furthermore, we found that the probabilistic approach offers a way of forecasting even more accurately while effectively discarding uncertain predictions. We demonstrate for the first time that probabilistic deep learning can be used to forecast resting-state EEG time series. In the future, the developed model can enhance the real-time estimation of brain states in brain-computer interfaces and brain stimulation protocols. It may also be useful for answering neuroscientific questions and for diagnostic purposes.

Geometric features between the micro and macro scales produce an expressive family of visual effects grouped under the term "glints". Efficiently rendering these effects amounts to finding the highlights caused by the geometry under each pixel. To allow for fast rendering, we represent our faceted geometry as a 4D point process on an implicit multiscale grid, designed to efficiently find the facets most likely to cause a highlight. The facets' normals are generated to match a given micro-facet normal distribution such as Trowbridge-Reitz (GGX) or Beckmann, to which our model converges under increasing surface area. Our method is simple to implement, memory-and-precomputation-free, allows for importance sampling and covers a wide range of different appearances such as anisotropic as well as individually colored particles. We provide a base implementation as a standalone fragment shader.

Diffusion models currently dominate the field of data- driven image synthesis with their unparalleled scaling to large datasets. In this paper, we identify and rectify several causes for uneven and ineffective training in the popular ADM diffusion model architecture, without altering its high- level structure. Observing uncontrolled magnitude changes and imbalances in both the network activations and weights over the course of training, we redesign the network layers to preserve activation, weight, and update magnitudes on ex- pectation. We find that systematic application of this philoso- phy eliminates the observed drifts and imbalances, resulting in considerably better networks at equal computational com- plexity. Our modifications improve the previous record FID of 2.41 in ImageNet-512 synthesis to 1.81, achieved using fast deterministic sampling. As an independent contribution, we present a method for setting the exponential moving average (EMA) parameters post-hoc, i.e., after completing the training run. This allows precise tuning of EMA length without the cost of performing several training runs, and reveals its surprising interactions with network architecture, training time, and guidance.

The primary axes of interest in image-generating diffusion models are image quality, the amount of variation in the results, and how well the results align with a given condition, e.g., a class label or a text prompt. The popular classifier-free guidance approach uses an unconditional model to guide a conditional model, leading to simultaneously better prompt alignment and higher-quality images at the cost of reduced variation. These effects seem inherently entangled, and thus hard to control. We make the surprising observation that it is possible to obtain disentangled control over image quality without compromising the amount of variation by guiding generation using a smaller, less-trained version of the model itself rather than an unconditional model. This leads to significant improvements in ImageNet generation, setting record FIDs of 1.01 for 64x64 and 1.25 for 512x512, using publicly available networks. Furthermore, the method is also applicable to unconditional diffusion models, drastically improving their quality.

Guidance is a crucial technique for extracting the best performance out of image-generating diffusion models. Traditionally, a constant guidance weight has been applied throughout the sampling chain of an image. We show that guidance is clearly harmful toward the beginning of the chain (high noise levels), largely unnecessary toward the end (low noise levels), and only beneficial in the middle. We thus restrict it to a specific range of noise levels, improving both the inference speed and result quality. This limited guidance interval improves the record FID in ImageNet-512 significantly, from 1.81 to 1.40. We show that it is quantitatively and qualitatively beneficial across different sampler parameters, network architectures, and datasets, including the large-scale setting of Stable Diffusion XL. We thus suggest exposing the guidance interval as a hyperparameter in all diffusion models that use guidance.

This paper presents CQT-Diff, a data-driven generative audio model that can, once trained, be used for solving various different audio inverse problems in a problem-agnostic setting. CQT-Diff is a neural diffusion model with an architecture that is carefully constructed to exploit pitch-equivariant symmetries in music. This is achieved by preconditioning the model with an invertible Constant-Q Transform (CQT), whose logarithmically-spaced frequency axis represents pitch equivariance as translation equivariance. The proposed method is evaluated with solo piano music, using objective and subjective metrics in three different and varied tasks: audio bandwidth extension, inpainting, and declipping. The results show that CQT-Diff outperforms the compared baselines and ablations in audio bandwidth extension and, without retraining, delivers competitive performance against modern baselines in audio inpainting and declipping. This work represents the first diffusion-based general framework for solving inverse problems in audio processing.

We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time while maintaining consistencies expected in real environments, such as plausible dynamics and object persistence. A common failure case is for content to never change due to over-reliance on inductive bias to provide temporal consistency, such as a single latent code that dictates content for the entire video. On the other extreme, without long-term consistency, generated videos may morph unrealistically between different scenes. To address these limitations, we prioritize the time axis by redesigning the temporal latent representation and learning long-term consistency from data by training on longer videos. We leverage a two-phase training strategy, where we separately train using longer videos at a low resolution and shorter videos at a high resolution. To evaluate the capabilities of our model, we introduce two new benchmark datasets with explicit focus on long-term temporal dynamics.

Time-lapse image sequences offer visually compelling insights into dynamic processes that are too slow to observe in real time. However, playing a long time-lapse sequence back as a video often results in distracting flicker due to random effects, such as weather, as well as cyclic effects, such as the day-night cycle. We introduce the problem of disentangling time-lapse sequences in a way that allows separate, after-the-fact control of overall trends, cyclic effects, and random effects in the images, and describe a technique based on data-driven generative models that achieves this goal. This enables us to "re-render" the sequences in ways that would not be possible with the input images alone. For example, we can stabilize a long sequence to focus on plant growth over many months, under selectable, consistent weather. Our approach is based on Generative Adversarial Networks (GAN) that are conditioned with the time coordinate of the time-lapse sequence. Our architecture and training procedure are designed so that the networks learn to model random variations, such as weather, using the GAN's latent space, and to disentangle overall trends and cyclic variations by feeding the conditioning time label to the model using Fourier features with specific frequencies. We show that our models are robust to defects in the training data, enabling us to amend some of the practical difficulties in capturing long time-lapse sequences, such as temporary occlusions, uneven frame spacing, and missing frames.

We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner. This manifests itself as, e.g., detail appearing to be glued to image coordinates instead of the surfaces of depicted objects. We trace the root cause to careless signal processing that causes aliasing in the generator network. Interpreting all signals in the network as continuous, we derive generally applicable, small architectural changes that guarantee that unwanted information cannot leak into the hierarchical synthesis process. The resulting networks match the FID of StyleGAN2 but differ dramatically in their internal representations, and they are fully equivariant to translation and rotation even at subpixel scales. Our results pave the way for generative models better suited for video and animation.

A common problem of mid-air interaction is excessive arm fatigue, known as the "Gorilla arm" effect. To predict and prevent such problems at a low cost, we investigate user testing of mid-air interaction without real users, utilizing biomechanically simulated AI agents trained using deep Reinforcement Learning (RL). We implement this in a pointing task and four experimental conditions, demonstrating that the simulated fatigue data matches human fatigue data. We also compare two effort models: 1) instantaneous joint torques commonly used in computer animation and robotics, and 2) the recent Three Compartment Controller (3CC-) model from biomechanical literature. 3CC- yields movements that are both more efficient and relaxed, whereas with instantaneous joint torques, the RL agent can easily generate movements that are quickly tiring or only reach the targets slowly and inaccurately. Our work demonstrates that deep RL combined with the 3CC- provides a viable tool for predicting both interaction movements and user experiencein silico, without users.

The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images. In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably attribute a generated image to a particular network. We furthermore visualize how well the generator utilizes its output resolution, and identify a capacity problem, motivating us to train larger models for additional quality improvements. Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.

This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. We identify important latent directions based on Principal Component Analysis (PCA) applied either in latent space or feature space. Then, we show that a large number of interpretable controls can be defined by layer-wise perturbation along the principal directions. Moreover, we show that BigGAN can be controlled with layer-wise inputs in a StyleGAN-like manner. We show results on different GANs trained on various datasets, and demonstrate good qualitative matches to edit directions found through earlier supervised approaches.

Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images. We expect this to open up new application domains for GANs. We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5.59 to 2.42.

We present a modular differentiable renderer design that yields performance superior to previous methods by leveraging existing, highly optimized hardware graphics pipelines. Our design supports all crucial operations in a modern graphics pipeline: rasterizing large numbers of triangles, attribute interpolation, filtered texture lookups, as well as user-programmable shading and geometry processing, all in high resolutions. Our modular primitives allow custom, high-performance graphics pipelines to be built directly within automatic differentiation frameworks such as PyTorch or TensorFlow. As a motivating application, we formulate facial performance capture as an inverse rendering problem and show that it can be solved efficiently using our tools. Our results indicate that this simple and straightforward approach achieves excellent geometric correspondence between rendered results and reference imagery.

Unsupervised image-to-image translation methods learn to map images in a given class to an analogous image in a different class, drawing on unstructured (non-registered) datasets of images. While remarkably successful, current methods require access to many images in both source and destination classes at training time. We argue this greatly limits their use. Drawing inspiration from the human capability of picking up the essence of a novel object from a small number of examples and generalizing from there, we seek a few-shot, unsupervised image-to-image translation algorithm that works on previously unseen target classes that are specified, at test time, only by a few example images. Our model achieves this few-shot generation capability by coupling an adversarial training scheme with a novel network design. Through extensive experimental validation and comparisons to several baseline methods on benchmark datasets, we verify the effectiveness of the proposed framework. Our implementation and datasets are available at https://github.com/NVlabs/FUNIT.

Many machine learning models operate on images, but ignore the fact that images are 2D projections formed by 3D geometry interacting with light, in a process called rendering. Enabling ML models to understand image formation might be key for generalization. However, due to an essential rasterization step involving discrete assignment operations, rendering pipelines are non-differentiable and thus largely inaccessible to gradient-based ML techniques. In this paper, we present DIB-Render, a novel rendering framework through which gradients can be analytically computed. Key to our approach is to view rasterization as a weighted interpolation, allowing image gradients to back-propagate through various standard vertex shaders within a single framework. Our approach supports optimizing over vertex positions, colors, normals, light directions and texture coordinates, and allows us to incorporate various well-known lighting models from graphics. We showcase our approach in two ML applications: single-image 3D object prediction, and 3D textured object generation, both trained using exclusively 2D supervision.

The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research. We present an evaluation metric that can separately and reliably measure both of these aspects in image generation tasks by forming explicit, non-parametric representations of the manifolds of real and generated data. We demonstrate the effectiveness of our metric in StyleGAN and BigGAN by providing several illustrative examples where existing metrics yield uninformative or contradictory results. Furthermore, we analyze multiple design variants of StyleGAN to better understand the relationships between the model architecture, training methods, and the properties of the resulting sample distribution. In the process, we identify new variants that improve the state-of-the-art. We also perform the first principled analysis of truncation methods and identify an improved method. Finally, we extend our metric to estimate the perceptual quality of individual samples, and use this to study latent space interpolations.

We describe a novel method for training high-quality image denoising models based on unorganized collections of corrupted images. The training does not need access to clean reference images, or explicit pairs of corrupted images, and can thus be applied in situations where such data is unacceptably expensive or impossible to acquire. We build on a recent technique that removes the need for reference data by employing networks with a "blind spot" in the receptive field, and significantly improve two key aspects: image quality and training efficiency. Our result quality is on par with state-of-the-art neural network denoisers in the case of i.i.d. additive Gaussian noise, and not far behind with Poisson and impulse noise. We also successfully handle cases where parameters of the noise model are variable and/or unknown in both training and evaluation data.

Abstract This paper proposes a new methodology for measuring the error of unbiased physically based rendering algorithms. The current state of the art includes mean squared error (MSE) based metrics and visual comparisons of equal‐time renderings of competing algorithms. Neither is satisfying as MSE does not describe behavior and can exhibit significant variance, and visual comparisons are inherently subjective. Our contribution is two‐fold: First, we propose to compute many short renderings instead of a single long run and use the short renderings to estimate MSE expectation and variance as well as per‐pixel standard deviation. An algorithm that achieves good results in most runs, but with occasional outliers is essentially unreliable, which we wish to quantify numerically. We use per‐pixel standard deviation to identify problematic lighting effects of rendering algorithms. The second contribution is the error spectrum ensemble (ESE), a tool for measuring the distribution of error over frequencies. The ESE serves two purposes: It reveals correlation between pixels and can be used to detect outliers, which offset the amount of error substantially.

Denoising has proven to be useful to efficiently generate high-quality Monte Carlo renderings. Traditional pixel-based denoisers exploit summary statistics of a pixel's sample distributions, which discards much of the samples' information and limits their denoising power. On the other hand, sample-based techniques tend to be slow and have difficulties handling general transport scenarios. We present the first convolutional network that can learn to denoise Monte Carlo renderings directly from the samples. Learning the mapping between samples and images creates new challenges for the network architecture design: the order of the samples is arbitrary, and they should be treated in a permutation invariant manner. To address these challenges, we develop a novel kernel-predicting architecture that splats individual samples onto nearby pixels. Splatting is a natural solution to situations such as motion blur, depth-of-field and many light transport paths, where it is easier to predict which pixels a sample contributes to, rather than a gather approach that needs to figure out, for each pixel, which samples (or nearby pixels) are relevant. Compared to previous state-of-the-art methods, ours is robust to the severe noise of low-sample count images (e.g. 8 samples per pixel) and yields higher-quality results both visually and numerically. Our approach retains the generality and efficiency of pixel-space methods while enjoying the expressiveness and accuracy of the more complex sample-based approaches.

It has been shown that rendering in the gradient domain, i.e., estimating finite difference gradients of image intensity using correlated samples, and combining them with direct estimates of pixel intensities by solving a screened Poisson problem, often offers fundamental benefits over merely sampling pixel intensities. The reasons can be traced to the frequency content of the light transport integrand and its interplay with the gradient operator. However, while they often yield state of the art performance among algorithms that are based on Monte Carlo sampling alone, gradient-domain rendering algorithms have, until now, not generally been competitive with techniques that combine Monte Carlo sampling with post-hoc noise removal using sophisticated non-linear filtering. Drawing on the power of modern convolutional neural networks, we propose a novel reconstruction method for gradient-domain rendering. Our technique replaces the screened Poisson solver of previous gradient-domain techniques with a novel dense variant of the U-Net autoencoder, additionally taking auxiliary feature buffers as inputs. We optimize our network to minimize a perceptual image distance metric calibrated to the human visual system. Our results significantly improve the quality obtained from gradient-domain path tracing, allowing it to overtake state-of-the-art comparison techniques that denoise traditional Monte Carlo samplings. In particular, we observe that the correlated gradient samples --- that offer information about the smoothness of the integrand unavailable in standard Monte Carlo sampling --- notably improve image quality compared to an equally powerful neural model that does not make use of gradient samples.

We apply basic statistical reasoning to signal reconstruction by machine learning - learning to map corrupted observations to clean signals - with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denoising synthetic Monte Carlo images, and reconstruction of undersampled MRI scans - all corrupted by different processes - based on noisy data only.

Gradient-based methods are becoming increasingly important for computer graphics, machine learning, and computer vision. The ability to compute gradients is crucial to optimization, inverse problems, and deep learning. In rendering, the gradient is required with respect to variables such as camera parameters, light sources, scene geometry, or material appearance. However, computing the gradient of rendering is challenging because the rendering integral includes visibility terms that are not differentiable. Previous work on differentiable rendering has focused on approximate solutions. They often do not handle secondary effects such as shadows or global illumination, or they do not provide the gradient with respect to variables other than pixel coordinates. We introduce a general-purpose differentiable ray tracer, which, to our knowledge, is the first comprehensive solution that is able to compute derivatives of scalar functions over a rendered image with respect to arbitrary scene parameters such as camera pose, scene geometry, materials, and lighting parameters. The key to our method is a novel edge sampling algorithm that directly samples the Dirac delta functions introduced by the derivatives of the discontinuous integrand. We also develop efficient importance sampling methods based on spatial hierarchies. Our method can generate gradients in times running from seconds to minutes depending on scene complexity and desired precision. We interface our differentiable ray tracer with the deep learning library PyTorch and show prototype applications in inverse rendering and the generation of adversarial examples for neural networks.

Implementing Monte Carlo integration requires significant domain expertise. While simple samplers, such as unidirectional path tracing, are relatively forgiving, more complex algorithms, such as bidirectional path tracing or Metropolis methods, are notoriously difficult to implement correctly. We propose Aether, an embedded domain specific language for Monte Carlo integration, which offers primitives for writing concise and correct-by-construction sampling and probability code. The user is tasked with writing sampling code, while our compiler automatically generates the code necessary for evaluating PDFs as well as the book keeping and combination of multiple sampling strategies. Our language focuses on ease of implementation for rapid exploration, at the cost of run time performance. We demonstrate the effectiveness of the language by implementing several challenging rendering algorithms as well as a new algorithm, which would otherwise be prohibitively difficult.

We present a machine learning technique for driving 3D facial animation by audio input in real time and with low latency. Our deep neural network learns a mapping from input waveforms to the 3D vertex coordinates of a face model, and simultaneously discovers a compact, latent code that disambiguates the variations in facial expression that cannot be explained by the audio alone. During inference, the latent code can be used as an intuitive control for the emotional state of the face puppet. We train our network with 3--5 minutes of high-quality animation data obtained using traditional, vision-based performance capture methods. Even though our primary goal is to model the speaking style of a single actor, our model yields reasonable results even when driven with audio from other speakers with different gender, accent, or language, as we demonstrate with a user study. The results are applicable to in-game dialogue, low-cost localization, virtual reality avatars, and telepresence.

We present a direct-to-indirect transport technique that enables accurate real-time rendering of indirect illumination in mostly static scenes of complexity on par with modern games while supporting fully dynamic lights, cameras and diffuse surface materials. Our key contribution is an algorithm for reconstructing the incident radiance field from a sparse set of local samples --- radiance probes --- by incorporating mutual visibility into the reconstruction filter. To compute global illumination, we factorize the direct-to-indirect transport operator into global and local parts, sample the global transport with sparse radiance probes at real-time, and use the sampled radiance field as input to our precomputed local reconstruction operator to obtain indirect radiance. In contrast to previous methods aiming to encode the global direct-to-indirect transport operator, our precomputed data is local in the sense that it needs no long-range interactions between probes and receivers, and every receiver depends only on a small, constant number of nearby radiance probes, aiding compression, storage, and iterative workflows. While not as accurate, we demonstrate that our method can also be used for rendering indirect illumination on glossy surfaces, and approximating global illumination in scenes with large-scale dynamic geometry.

Instant Radiosity and its derivatives are interactive methods for efficiently estimating global (indirect) illumination. They represent the last indirect bounce of illumination before the camera as the composite radiance field emitted by a set of virtual point light sources (VPLs). In complex scenes, current algorithms suffer from a difficult combination of two issues: it remains a challenge to distribute VPLs in a manner that simultaneously gives a high-quality indirect illumination solution for each frame, and to do so in a temporally coherent manner. We address both issues by building, and maintaining over time, an adaptive and temporally coherent distribution of VPLs in locations where they bring indirect light to the image. We introduce a novel heuristic sampling method that strives to only move as few of the VPLs between frames as possible. The result is, to the best of our knowledge, the first interactive global illumination algorithm that works in complex, highly-occluded scenes, suffers little from temporal flickering, supports moving cameras and light sources, and is output-sensitive in the sense that it places VPLs in locations that matter most to the final result.

Instant Radiosity and its derivatives are interactive methods for efficiently estimating global (indirect) illumination. They represent the last indirect bounce of illumination before the camera as the composite radiance field emitted by a set of virtual point light sources (VPLs). In complex scenes, current algorithms suffer from a difficult combination of two issues: it remains a challenge to distribute VPLs in a manner that simultaneously gives a high-quality indirect illumination solution for each frame, and does so in a temporally coherent manner. We address both issues by building, and maintaining over time, an adaptive and temporally coherent distribution of VPLs in locations where they bring indirect light to the image. We introduce a novel heuristic sampling method that strives to only move as few of the VPLs between frames as possible. The result is, to the best of our knowledge, the first interactive global illumination algorithm that works in complex, highly-occluded scenes, suffers little from temporal flickering, supports moving cameras and light sources, and is output-sensitive in the sense that it places VPLs in locations that matter most to the final result.

We extend parametric texture synthesis to capture rich, spatially varying parametric reflectance models from a single image. Our input is a single head-lit flash image of a mostly flat, mostly stationary (textured) surface, and the output is a tile of SVBRDF parameters that reproduce the appearance of the material. No user intervention is required. Our key insight is to make use of a recent, powerful texture descriptor based on deep convolutional neural network statistics for "softly" comparing the model prediction and the examplars without requiring an explicit point-to-point correspondence between them. This is in contrast to traditional reflectance capture that requires pointwise constraints between inputs and outputs under varying viewing and lighting conditions. Seen through this lens, our method is an indirect algorithm for fitting photorealistic SVBRDFs. The problem is severely ill-posed and non-convex. To guide the optimizer towards desirable solutions, we introduce a soft Fourier-domain prior for encouraging spatial stationarity of the reflectance parameters and their correlations, and a complementary preconditioning technique that enables efficient exploration of such solutions by L-BFGS, a standard non-linear numerical optimizer.

We present a novel approach to improve temporal coherence in Monte Carlo renderings of animation sequences. Unlike other approaches that exploit temporal coherence in a post-process, our technique does so already during sampling. Building on previous gradient-domain rendering techniques that sample finite differences over the image plane, we introduce temporal finite differences and formulate a corresponding 3D spatio-temporal screened Poisson reconstruction problem that is solved over windowed batches of several frames simultaneously. We further extend our approach to include second order, mixed spatio-temporal differences, an improved technique to compute temporal differences exploiting motion vectors, and adaptive sampling. Our algorithm can be built on a gradient-domain path tracer without large modifications. In particular, we do not require the ability to evaluate animation paths over multiple frames. We demonstrate that our approach effectively reduces temporal flickering in animation sequences, significantly improving the visual quality compared to both path tracing and gradient-domain rendering of individual frames.

Abstract Monte Carlo integration is firmly established as the basis for most practical realistic image synthesis algorithms because of its flexibility and generality. However, the visual quality of rendered images often suffers from estimator variance, which appears as visually distracting noise. Adaptive sampling and reconstruction algorithms reduce variance by controlling the sampling density and aggregating samples in a reconstruction step, possibly over large image regions. In this paper we survey recent advances in this area. We distinguish between “a priori” methods that analyze the light transport equations and derive sampling rates and reconstruction filters from this analysis, and “a posteriori” methods that apply statistical techniques to sets of samples to drive the adaptive sampling and reconstruction process. They typically estimate the errors of several reconstruction filters, and select the best filter locally to minimize error. We discuss advantages and disadvantages of recent state‐of‐the‐art techniques, and provide visual and quantitative comparisons. Some of these techniques are proving useful in real‐world applications, and we aim to provide an overview for practitioners and researchers to assess these approaches. In addition, we discuss directions for potential further improvements.

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.

We introduce gradient-domain rendering for Monte Carlo image synthesis. While previous gradient-domain Metropolis Light Transport sought to distribute more samples in areas of high gradients, we show, in contrast, that estimating image gradients is also possible using standard (non-Metropolis) Monte Carlo algorithms, and furthermore, that even without changing the sample distribution, this often leads to significant error reduction. This broadens the applicability of gradient rendering considerably. To gain insight into the conditions under which gradient-domain sampling is beneficial, we present a frequency analysis that compares Monte Carlo sampling of gradients followed by Poisson reconstruction to traditional Monte Carlo sampling. Finally, we describe Gradient-Domain Path Tracing (G-PT), a relatively simple modification of the standard path tracing algorithm that can yield far superior results.

The simulation of light transport in the presence of multi-bounce glossy effects and motion is challenging because the integrand is high dimensional and areas of high-contribution tend to be narrow and hard to sample. We present a Markov Chain Monte Carlo (MCMC) rendering algorithm that extends Metropolis Light Transport by automatically and explicitly adapting to the local shape of the integrand, thereby increasing the acceptance rate. Our algorithm characterizes the local behavior of throughput in path space using its gradient as well as its Hessian. In particular, the Hessian is able to capture the strong anisotropy of the integrand. We obtain the derivatives using automatic differentiation, which makes our solution general and easy to extend to additional sampling dimensions such as time. However, the resulting second order Taylor expansion is not a proper distribution and cannot be used directly for importance sampling. Instead, we use ideas from Hamiltonian Monte-Carlo and simulate the Hamiltonian dynamics in a flipped version of the Taylor expansion where gravity pulls particles towards the high-contribution region. Whereas such methods usually require numerical integration, we show that our quadratic landscape leads to a closed-form anisotropic Gaussian distribution for the final particle positions, and it results in a standard Metropolis-Hastings algorithm. Our method excels at rendering glossy-to-glossy reflections on small and highly curved surfaces. Furthermore, unlike previous work that derives sampling anisotropy with pen and paper and only considers specific effects such as specular BSDFs, we characterize the local shape of throughput through automatic differentiation. This makes our approach very general. In particular, our method is the first MCMC rendering algorithm that is able to resolve the anisotropy in the time dimension and render difficult moving caustics.

Abstract We present a method for extreme occluder simplification. We take a triangle soup as input, and produce a small set of polygons with closely matching occlusion properties. In contrast to methods that optimize the original geometry, our algorithm has very few requirements for the input— specifically, the input does not need to be a watertight, two‐manifold mesh. This robustness is achieved by working on a well‐behaved, discretized representation of the input instead of the original, potentially badly structured geometry. We first formulate the algorithm for individual occluders, and further introduce a hierarchy for handling large, complex scenes.

We present a Model-Predictive Control (MPC) system for online synthesis of interactive and physically valid character motion. Our system enables a complex (36-DOF) 3D human character model to balance in a given pose, dodge projectiles, and improvise a get up strategy if forced to lose balance, all in a dynamic and unpredictable environment. Such contact-rich, predictive and reactive motions have previously only been generated offline or using a handcrafted state machine or a dataset of reference motions, which our system does not require. For each animation frame, our system generates trajectories of character control parameters for the near future --- a few seconds --- using Sequential Monte Carlo sampling. Our main technical contribution is a multimodal, tree-based sampler that simultaneously explores multiple different near-term control strategies represented as parameter splines. The strategies represented by each sample are evaluated in parallel using a causal physics engine. The best strategy, as determined by an objective function measuring goal achievement, fluidity of motion, etc., is used as the control signal for the current frame, but maintaining multiple hypotheses is crucial for adapting to dynamically changing environments.

We present a generalized framework for gradient-domain Metropolis rendering, and introduce three techniques to reduce sampling artifacts and variance. The first one is a heuristic weighting strategy that combines several sampling techniques to avoid outliers. The second one is an improved mapping to generate offset paths required for computing gradients. Here we leverage the properties of manifold walks in path space to cancel out singularities. Finally, the third technique introduces generalized screen space gradient kernels. This approach aligns the gradient kernels with image structures such as texture edges and geometric discontinuities to obtain sparser gradients than with the conventional gradient kernel. We implement our framework on top of an existing Metropolis sampler, and we demonstrate significant improvements in visual and numerical quality of our results compared to previous work.

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.

We introduce a novel Metropolis rendering algorithm that directly computes image gradients, and reconstructs the final image from the gradients by solving a Poisson equation. The reconstruction is aided by a low-fidelity approximation of the image computed during gradient sampling. As an extension of path-space Metropolis light transport, our algorithm is well suited for difficult transport scenarios. We demonstrate that our method outperforms the state-of-the-art in several well-known test scenes. Additionally, we analyze the spectral properties of gradient-domain sampling, and compare it to the traditional image-domain sampling.

Stochastic techniques for rendering indirect illumination suffer from noise due to the variance in the integrand. In this paper, we describe a general reconstruction technique that exploits anisotropy in the light field and permits efficient reuse of input samples between pixels or world-space locations, multiplying the effective sampling rate by a large factor. Our technique introduces visibility-aware anisotropic reconstruction to indirect illumination, ambient occlusion and glossy reflections. It operates on point samples without knowledge of the scene, and can thus be seen as an advanced image filter. Our results show dramatic improvement in image quality while using very sparse input samplings.

We present a novel method for increasing the efficiency of stochastic rasterization of motion and defocus blur. Contrary to earlier approaches, our method is efficient even with the low sampling densities commonly encountered in realtime rendering, while allowing the use of arbitrary sampling patterns for maximal image quality. Our clipless dual-space formulation avoids problems with triangles that cross the camera plane during the shutter interval. The method is also simple to plug into existing rendering systems.

Traditionally, effects that require evaluating multidimensional integrals for each pixel, such as motion blur, depth of field, and soft shadows, suffer from noise due to the variance of the high-dimensional integrand. In this paper, we describe a general reconstruction technique that exploits the anisotropy in the temporal light field and permits efficient reuse of samples between pixels, multiplying the effective sampling rate by a large factor. We show that our technique can be applied in situations that are challenging or impossible for previous anisotropic reconstruction methods, and that it can yield good results with very sparse inputs. We demonstrate our method for simultaneous motion blur, depth of field, and soft shadows.

We propose a generalized approach to decoupling shading from visibility sampling in graphics pipelines, which we call decoupled sampling . Decoupled sampling enables stochastic supersampling of motion and defocus blur at reduced shading cost, as well as controllable or adaptive shading rates which trade off shading quality for performance. It can be thought of as a generalization of multisample antialiasing (MSAA) to support complex and dynamic mappings from visibility to shading samples, as introduced by motion and defocus blur and adaptive shading. It works by defining a many-to-one hash from visibility to shading samples, and using a buffer to memoize shading samples and exploit reuse across visibility samples. Decoupled sampling is inspired by the Reyes rendering architecture, but like traditional graphics pipelines, it shades fragments rather than micropolygon vertices, decoupling shading from the geometry sampling rate. Also unlike Reyes, decoupled sampling only shades fragments after precise computation of visibility, reducing overshading. We present extensions of two modern graphics pipelines to support decoupled sampling: a GPU-style sort-last fragment architecture, and a Larrabee-style sort-middle pipeline. We study the architectural implications of decoupled sampling and blur, and derive end-to-end performance estimates on real applications through an instrumented functional simulator. We demonstrate high-quality motion and defocus blur, as well as variable and adaptive shading rates.

Abstract Clothoid splines are gaining popularity as a curve representation due to their intrinsically pleasing curvature, which varies piecewise linearly over arc length. However, constructing them from hand‐drawn strokes remains difficult. Building on recent results, we describe a novel algorithm for approximating a sketched stroke with a fair (i.e., visually pleasing) clothoid spline. Fairness depends on proper segmentation of the stroke into curve primitives — lines, arcs, and clothoids. Our main idea is to cast the segmentation as a shortest path problem on a carefully constructed weighted graph. The nodes in our graph correspond to a vastly overcomplete set of curve primitives that are fit to every subsegment of the sketch, and edges correspond to transitions of a specified degree of continuity between curve primitives. The shortest path in the graph corresponds to a desirable segmentation of the input curve. Once the segmentation is found, the primitives are fit to the curve using non‐linear constrained optimization. We demonstrate that the curves produced by our method have good curvature profiles, while staying close to the user sketch.

Volumetric effects such as beams of light through participating media are an important component in the appearance of the natural world. Many such effects can be faithfully modeled by a single scattering medium. In the presence of shadows, rendering these effects can be prohibitively expensive: current algorithms are based on ray marching, i.e., integrating the illumination scattered towards the camera along each view ray, modulated by visibility to the light source at each sample. Visibility must be determined for each sample using shadow rays or shadow-map lookups. We observe that in a suitably chosen coordinate system, the visibility function has a regular structure that we can exploit for significant acceleration compared to brute force sampling. We propose an efficient algorithm based on partial sum trees for computing the scattering integrals in a single-scattering homogeneous medium. On a CPU, we achieve speedups of 17--120x over ray marching.

We introduce a meshless hierarchical representation for solving light transport problems. Precomputed radiance transfer (PRT) and finite elements require a discrete representation of illumination over the scene. Non-hierarchical approaches such as per-vertex values are simple to implement, but lead to long precomputation. Hierarchical bases like wavelets lead to dramatic acceleration, but in their basic form they work well only on flat or smooth surfaces. We introduce a hierarchical function basis induced by scattered data approximation. It is decoupled from the geometric representation, allowing the hierarchical representation of illumination on complex objects. We present simple data structures and algorithms for constructing and evaluating the basis functions. Due to its hierarchical nature, our representation adapts to the complexity of the illumination, and can be queried at different scales. We demonstrate the power of the new basis in a novel precomputed direct-to-indirect light transport algorithm that greatly increases the complexity of scenes that can be handled by PRT approaches.

Several types of methods precompute or capture light transport operators in either virtual or real scenes. Precomputed radiance transfer methods interactively render realistic images of static scenes under dynamic incident illumination, while reflectance field techniques capture an appearance model of a real scene for relighting purposes. In this article we present a unifying mathematical framework for methods that precompute or capture light transport operators, and characterize a large body of earlier work in its terms. The framework is given in the form of an operator equation that extends the rendering equation to account for a constrained space of emissions. The connections between traditional global illumination methods and precomputed transfer techniques become apparent through the explicit equation. Based on insight provided by the unifying view, we outline possibilities for new methods, particularly the wider adaptation of previous, hierarchical finite element techniques for efficient computation of the transport operators.

Abstract We identify and analyze several performance problems in a state‐of‐the‐art physically‐based soft shadow volume algorithm, and present an improved method that alleviates these problems by replacing an overly conservative spatial acceleration structure by a more efficient one. The new technique consistently outperforms both the previous method and a ray tracing‐based reference solution in several realistic situations while retaining the correctness of the solution and other desirable characteristics of the previous method. These include the unintrusiveness of the original algorithm, meaning that our method can be used as a black‐box shadow solver in any offline renderer without requiring multiple passes over the image or other special accommodation. We achieve speedup factors from 1.6 to 12.3 when compared to the previous method. Categories and Subject Descriptors (according to ACM CCS): I.3.7 [Three‐Dimensional Graphics and Realism]: Shadowing

We present a new, fast algorithm for rendering physically-based soft shadows in ray tracing-based renderers. Our method replaces the hundreds of shadow rays commonly used in stochastic ray tracers with a single shadow ray and a local reconstruction of the visibility function. Compared to tracing the shadow rays. our algorithm produces exactly the same image while executing one to two orders of magnitude faster in the test scenes used. Our first contribution is a two-stage method for quickly determining the silhouette edges that overlap an area light source, as seen from the point to be shaded. Secondly, we show that these partial silhouettes of occluders, along with a single shadow ray, are sufficient for reconstructing the visibility function between the point and the light source.

Precomputed Radiance Transfer allows interactive rendering of objects illuminated by low-frequency environment maps, including self-shadowing and interreflections. The expensive integration of incident lighting is partially precomputed and stored as matrices.Incorporating anisotropic, glossy BRDFs into precomputed radiance transfer has been previously shown to be possible, but none of the previous methods offer real-time performance. We propose a new method, matrix radiance transfer, which significantly speeds up exit radiance computation and allows anisotropic BRDFs. We generalize the previous radiance transfer methods to work with a matrix representation of the BRDF and optimize exit radiance computation by expressing the exit radiance in a new, directionally locally supported basis set instead of the spherical harmonics. To determine exit radiance, our method performs four dot products per vertex in contrast to previous methods, where a full matrix-vector multiply is required. Image quality can be controlled by adapting the number of basis functions. We compress our radiance transfer matrices through principal component analysis (PCA). We show that it is possible to render directly from the PCA representation, which also enables the user to trade interactively between quality and speed.