Abstract: We present a novel approach that enables photo-realistic re-animation of portrait videos using only an input video. In contrast to existing approaches that are restricted to manipulations of facial expressions only, we are the first to transfer the full 3D head position, head rotation, face expression, eye gaze, and eye blinking from a source actor to a portrait video of a target actor. The core of our approach is a generative neural network with a novel space-time architecture. The network takes as input synthetic renderings of a parametric face model, based on which it predicts photo-realistic video frames for a given target actor. The realism in this rendering-to-video transfer is achieved by careful adversarial training, and as a result, we can create modified target videos that mimic the behavior of the synthetically-created input. In order to enable source-to-target video re-animation, we render a synthetic target video with the reconstructed head animation parameters from a source video, and feed it into the trained network - thus taking full control of the target. With the ability to freely recombine source and target parameters, we are able to demonstrate a large variety of video rewrite applications without explicitly modeling hair, body or background. For instance, we can reenact the full head using interactive user-controlled editing, and realize high-fidelity visual dubbing. To demonstrate the high quality of our output, we conduct an extensive series of experiments and evaluations, where for instance a user study shows that our video edits are hard to detect.

Abstract: Scene representation-the process of converting visual sensory data into concise descriptions-is a requirement for intelligent behavior. Recent work has shown that neural networks excel at this task when provided with large, labeled datasets. However, removing the reliance on human labeling remains an important open problem. To this end, we introduce the Generative Query Network (GQN), a framework within which machines learn to represent scenes using only their own sensors. The GQN takes as input images of a scene taken from different viewpoints, constructs an internal representation, and uses this representation to predict the appearance of that scene from previously unobserved viewpoints. The GQN demonstrates representation learning without human labels or domain knowledge, paving the way toward machines that autonomously learn to understand the world around them.

Abstract: 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.

Abstract: The goal of our work is to complete the depth channel of an RGB-D image. Commodity-grade depth cameras often fail to sense depth for shiny, bright, transparent, and distant surfaces. To address this problem, we train a deep network that takes an RGB image as input and predicts dense surface normals and occlusion boundaries. Those predictions are then combined with raw depth observations provided by the RGB-D camera to solve for depths for all pixels, including those missing in the original observation. This method was chosen over others (e.g., inpainting depths directly) as the result of extensive experiments with a new depth completion benchmark dataset, where holes are filled in training data through the rendering of surface reconstructions created from multiview RGB-D scans. Experiments with different network inputs, depth representations, loss functions, optimization methods, inpainting methods, and deep depth estimation networks show that our proposed approach provides better depth completions than these alternatives.

Abstract: Free-viewpoint image-based rendering (IBR) is a standing challenge. IBR methods combine warped versions of input photos to synthesize a novel view. The image quality of this combination is directly affected by geometric inaccuracies of multi-view stereo (MVS) reconstruction and by view- and image-dependent effects that produce artifacts when contributions from different input views are blended. We present a new deep learning approach to blending for IBR, in which we use held-out real image data to learn blending weights to combine input photo contributions. Our Deep Blending method requires us to address several challenges to achieve our goal of interactive free-viewpoint IBR navigation. We first need to provide sufficiently accurate geometry so the Convolutional Neural Network (CNN) can succeed in finding correct blending weights. We do this by combining two different MVS reconstructions with complementary accuracy vs. completeness tradeoffs. To tightly integrate learning in an interactive IBR system, we need to adapt our rendering algorithm to produce a fixed number of input layers that can then be blended by the CNN. We generate training data with a variety of captured scenes, using each input photo as ground truth in a held-out approach. We also design the network architecture and the training loss to provide high quality novel view synthesis, while reducing temporal flickering artifacts. Our results demonstrate free-viewpoint IBR in a wide variety of scenes, clearly surpassing previous methods in visual quality, especially when moving far from the input cameras.

Abstract: We present a fast inverse-graphics framework for instance-level 3D scene understanding. We train a deep convolutional network that learns to map image regions to the full 3D shape and pose of all object instances in the image. Our method produces a compact 3D representation of the scene, which can be readily used for applications like autonomous driving. Many traditional 2D vision outputs, like instance segmentations and depth-maps, can be obtained by simply rendering our output 3D scene model. We exploit class-specific shape priors by learning a low dimensional shape-space from collections of CAD models. We present novel representations of shape and pose, that strive towards better 3D equivariance and generalization. In order to exploit rich supervisory signals in the form of 2D annotations like segmentation, we propose a differentiable Render-and-Compare loss that allows 3D shape and pose to be learned with 2D supervision. We evaluate our method on the challenging real-world datasets of Pascal3D+ and KITTI, where we achieve state-of-the-art results.

Abstract: Reconstructing shape and reflectance properties from images is a highly under-constrained problem, and has previously been addressed by using specialized hardware to capture calibrated data or by assuming known (or highly constrained) shape or reflectance. In contrast, we demonstrate that we can recover non-Lambertian, spatially-varying BRDFs and complex geometry belonging to any arbitrary shape class, from a single RGB image captured under a combination of unknown environment illumination and flash lighting. We achieve this by training a deep neural network to regress shape and reflectance from the image. Our network is able to address this problem because of three novel contributions: first, we build a large-scale dataset of procedurally generated shapes and real-world complex SVBRDFs that approximate real world appearance well. Second, single image inverse rendering requires reasoning at multiple scales, and we propose a cascade network structure that allows this in a tractable manner. Finally, we incorporate an in-network rendering layer that aids the reconstruction task by handling global illumination effects that are important for real-world scenes. Together, these contributions allow us to tackle the entire inverse rendering problem in a holistic manner and produce state-of-the-art results on both synthetic and real data.

Abstract: We present SfSNet, an end-to-end learning framework for producing an accurate decomposition of an unconstrained human face image into shape, reflectance and illuminance. SfSNet is designed to reflect a physical lambertian rendering model. SfSNet learns from a mixture of labeled synthetic and unlabeled real world images. This allows the network to capture low frequency variations from synthetic and high frequency details from real images through the photometric reconstruction loss. SfSNet consists of a new decomposition architecture with residual blocks that learns a complete separation of albedo and normal. This is used along with the original image to predict lighting. SfSNet produces significantly better quantitative and qualitative results than state-of-the-art methods for inverse rendering and independent normal and illumination estimation.

Abstract: Earlier work demonstrates the promise of deep-learning-based approaches for point cloud segmentation; however, these approaches need to be improved to be practically useful To this end, we introduce a new model SqueezeSegV2 that is more robust to dropout noise in LiDAR point clouds With improved model structure, training loss, batch normalization and additional input channel, SqueezeSegV2 achieves significant accuracy improvement when trained on real data Training models for point cloud segmentation requires large amounts of labeled point-cloud data, which is expensive to obtain To sidestep the cost of collection and annotation, simulators such as GTA-V can be used to create unlimited amounts of labeled, synthetic data However, due to domain shift, models trained on synthetic data often do not generalize well to the real world We address this problem with a domain-adaptation training pipeline consisting of three major components: 1) learned intensity rendering, 2) geodesic correlation alignment, and 3) progressive domain calibration When trained on real data, our new model exhibits segmentation accuracy improvements of 60-86% over the original SqueezeSeg When training our new model on synthetic data using the proposed domain adaptation pipeline, we nearly double test accuracy on real-world data, from 290% to 574% Our source code and synthetic dataset will be open-sourced

Abstract: This book provides a fundamental understanding of global illumination algorithms. It discusses a broad class of algorithms for realistic image synthesis and introduces a theoretical basis for the algorithms presented. Topics include: physics of light transport, Monte Carlo methods, general strategies for solving the rendering equation, stochastic path-tracing algorithms such as ray tracing and light tracing, stochastic radiosity including photon density estimation and hierarchical Monte Carlo radiosity, hybrid algorithms, metropolis light transport, irradiance caching, photon mapping and instant radiosity, beyond the rendering equation, image display and human perception. If you want to design and implement a global illumination rendering system or need to use and modify an existing system for your specific purpose, this book will give you the tools and the understanding to do so.

Abstract: As a classic statistical model of 3D facial shape and texture, 3D Morphable Model (3DMM) is widely used in facial analysis, e.g., model fitting, image synthesis. Conventional 3DMM is learned from a set of well-controlled 2D face images with associated 3D face scans, and represented by two sets of PCA basis functions. Due to the type and amount of training data, as well as the linear bases, the representation power of 3DMM can be limited. To address these problems, this paper proposes an innovative framework to learn a nonlinear 3DMM model from a large set of unconstrained face images, without collecting 3D face scans. Specifically, given a face image as input, a network encoder estimates the projection, shape and texture parameters. Two decoders serve as the nonlinear 3DMM to map from the shape and texture parameters to the 3D shape and texture, respectively. With the projection parameter, 3D shape, and texture, a novel analytically-differentiable rendering layer is designed to reconstruct the original input face. The entire network is end-to-end trainable with only weak supervision. We demonstrate the superior representation power of our nonlinear 3DMM over its linear counterpart, and its contribution to face alignment and 3D reconstruction.

Abstract: We introduce a deep appearance model for rendering the human face. Inspired by Active Appearance Models, we develop a data-driven rendering pipeline that learns a joint representation of facial geometry and appearance from a multiview capture setup. Vertex positions and view-specific textures are modeled using a deep variational autoencoder that captures complex nonlinear effects while producing a smooth and compact latent representation. View-specific texture enables the modeling of view-dependent effects such as specularity. In addition, it can also correct for imperfect geometry stemming from biased or low resolution estimates. This is a significant departure from the traditional graphics pipeline, which requires highly accurate geometry as well as all elements of the shading model to achieve realism through physically-inspired light transport. Acquiring such a high level of accuracy is difficult in practice, especially for complex and intricate parts of the face, such as eyelashes and the oral cavity. These are handled naturally by our approach, which does not rely on precise estimates of geometry. Instead, the shading model accommodates deficiencies in geometry though the flexibility afforded by the neural network employed. At inference time, we condition the decoding network on the viewpoint of the camera in order to generate the appropriate texture for rendering. The resulting system can be implemented simply using existing rendering engines through dynamic textures with flat lighting. This representation, together with a novel unsupervised technique for mapping images to facial states, results in a system that is naturally suited to real-time interactive settings such as Virtual Reality (VR).

Abstract: Texture, highlights, and shading are some of many visual cues that allow humans to perceive material appearance in single pictures. Yet, recovering spatially-varying bi-directional reflectance distribution functions (SVBRDFs) from a single image based on such cues has challenged researchers in computer graphics for decades. We tackle lightweight appearance capture by training a deep neural network to automatically extract and make sense of these visual cues. Once trained, our network is capable of recovering per-pixel normal, diffuse albedo, specular albedo and specular roughness from a single picture of a flat surface lit by a hand-held flash. We achieve this goal by introducing several innovations on training data acquisition and network design. For training, we leverage a large dataset of artist-created, procedural SVBRDFs which we sample and render under multiple lighting directions. We further amplify the data by material mixing to cover a wide diversity of shading effects, which allows our network to work across many material classes. Motivated by the observation that distant regions of a material sample often offer complementary visual cues, we design a network that combines an encoder-decoder convolutional track for local feature extraction with a fully-connected track for global feature extraction and propagation. Many important material effects are view-dependent, and as such ambiguous when observed in a single image. We tackle this challenge by defining the loss as a differentiable SVBRDF similarity metric that compares the renderings of the predicted maps against renderings of the ground truth from several lighting and viewing directions. Combined together, these novel ingredients bring clear improvement over state of the art methods for single-shot capture of spatially varying BRDFs.

Abstract: Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object detectors, as the labeling comes for free, and several approaches have been proposed to combine synthetic and real images for training. In this paper, we evaluate if ‘freezing’ the layers responsible for feature extraction to generic layers pre-trained on real images, and training only the remaining layers with plain OpenGL rendering may allow for training with synthetic images only. Our experiments with very recent deep architectures for object recognition (Faster-RCNN, R-FCN, Mask-RCNN) and image feature extractors (InceptionResnet and Resnet) show this simple approach performs surprisingly well.

Abstract: The illegal distribution of a digital movie is a common and significant threat to the film industry. With the advent of high-speed broadband Internet access, a pirated copy of a digital video can now be easily distributed to a global audience. A possible means of limiting this type of digital theft is digital video watermarking whereby additional information, called a watermark, is embedded in the host video. This watermark can be extracted at the decoder and used to determine whether the video content is watermarked. This paper presents a review of the digital video watermarking techniques in which their applications, challenges, and important properties are discussed, and categorizes them based on the domain in which they embed the watermark. It then provides an overview of a few emerging innovative solutions using watermarks. Protecting a 3D video by watermarking is an emerging area of research. The relevant 3D video watermarking techniques in the literature are classified based on the image-based representations of a 3D video in stereoscopic, depth-image-based rendering, and multi-view video watermarking. We discuss each technique, and then present a survey of the literature. Finally, we provide a summary of this paper and propose some future research directions.

Abstract: In this article we develop an image based rendering technique based on light field reconstruction from a limited set of perspective views acquired by cameras. Our approach utilizes sparse representation of epipolar-plane images (EPI) in shearlet transform domain. The shearlet transform has been specifically modified to handle the straight lines characteristic for EPI. The devised iterative regularization algorithm based on adaptive thresholding provides high-quality reconstruction results for relatively big disparities between neighboring views. The generated densely sampled light field of a given 3D scene is thus suitable for all applications which require light field reconstruction. The proposed algorithm compares favorably against state of the art depth image based rendering techniques and shows superior performance specifically in reconstructing scenes containing semi-transparent objects.

Abstract: We present a novel method to generate accurate and realistic clothing deformation from real data capture. Previous methods for realistic cloth modeling mainly rely on intensive computation of physics-based simulation (with numerous heuristic parameters), while models reconstructed from visual observations typically suffer from lack of geometric details. Here, we propose an original framework consisting of two modules that work jointly to represent global shape deformation as well as surface details with high fidelity. Global shape deformations are recovered from a subspace model learned from 3D data of clothed people in motion, while high frequency details are added to normal maps created using a conditional Generative Adversarial Network whose architecture is designed to enforce realism and temporal consistency. This leads to unprecedented high-quality rendering of clothing deformation sequences, where fine wrinkles from (real) high resolution observations can be recovered. In addition, as the model is learned independently from body shape and pose, the framework is suitable for applications that require retargeting (e.g., body animation). Our experiments show original high quality results with a flexible model. We claim an entirely data-driven approach to realistic cloth wrinkle generation is possible.

Abstract: We introduce Synscapes -- a synthetic dataset for street scene parsing created using photorealistic rendering techniques, and show state-of-the-art results for training and validation as well as new types of analysis. We study the behavior of networks trained on real data when performing inference on synthetic data: a key factor in determining the equivalence of simulation environments. We also compare the behavior of networks trained on synthetic data and evaluated on real-world data. Additionally, by analyzing pre-trained, existing segmentation and detection models, we illustrate how uncorrelated images along with a detailed set of annotations open up new avenues for analysis of computer vision systems, providing fine-grain information about how a model's performance changes according to factors such as distance, occlusion and relative object orientation.

Abstract: Intrinsic image decomposition is a challenging, long-standing computer vision problem for which ground truth data is very difficult to acquire. We explore the use of synthetic data for training CNN-based intrinsic image decomposition models, then applying these learned models to real-world images. To that end, we present CGIntrinsics, a new, large-scale dataset of physically-based rendered images of scenes with full ground truth decompositions. The rendering process we use is carefully designed to yield high-quality, realistic images, which we find to be crucial for this problem domain. We also propose a new end-to-end training method that learns better decompositions by leveraging CGIntrinsics, and optionally IIW and SAW, two recent datasets of sparse annotations on real-world images. Surprisingly, we find that a decomposition network trained solely on our synthetic data outperforms the state-of-the-art on both IIW and SAW, and performance improves even further when IIW and SAW data is added during training. Our work demonstrates the suprising effectiveness of carefully-rendered synthetic data for the intrinsic images task.

Abstract: Recent progress in deep generative models has led to tremendous breakthroughs in image generation. However, while existing models can synthesize photorealistic images, they lack an understanding of our underlying 3D world. We present a new generative model, Visual Object Networks (VON), synthesizing natural images of objects with a disentangled 3D representation. Inspired by classic graphics rendering pipelines, we unravel our image formation process into three conditionally independent factors---shape, viewpoint, and texture---and present an end-to-end adversarial learning framework that jointly models 3D shapes and 2D images. Our model first learns to synthesize 3D shapes that are indistinguishable from real shapes. It then renders the object's 2.5D sketches (i.e., silhouette and depth map) from its shape under a sampled viewpoint. Finally, it learns to add realistic texture to these 2.5D sketches to generate natural images. The VON not only generates images that are more realistic than state-of-the-art 2D image synthesis methods, but also enables many 3D operations such as changing the viewpoint of a generated image, editing of shape and texture, linear interpolation in texture and shape space, and transferring appearance across different objects and viewpoints.

Abstract: We present a deep learning-based technique to infer high-quality facial reflectance and geometry given a single unconstrained image of the subject, which may contain partial occlusions and arbitrary illumination conditions. The reconstructed high-resolution textures, which are generated in only a few seconds, include high-resolution skin surface reflectance maps, representing both the diffuse and specular albedo, and medium- and high-frequency displacement maps, thereby allowing us to render compelling digital avatars under novel lighting conditions. To extract this data, we train our deep neural networks with a high-quality skin reflectance and geometry database created with a state-of-the-art multi-view photometric stereo system using polarized gradient illumination. Given the raw facial texture map extracted from the input image, our neural networks synthesize complete reflectance and displacement maps, as well as complete missing regions caused by occlusions. The completed textures exhibit consistent quality throughout the face due to our network architecture, which propagates texture features from the visible region, resulting in high-fidelity details that are consistent with those seen in visible regions. We describe how this highly underconstrained problem is made tractable by dividing the full inference into smaller tasks, which are addressed by dedicated neural networks. We demonstrate the effectiveness of our network design with robust texture completion from images of faces that are largely occluded. With the inferred reflectance and geometry data, we demonstrate the rendering of high-fidelity 3D avatars from a variety of subjects captured under different lighting conditions. In addition, we perform evaluations demonstrating that our method can infer plausible facial reflectance and geometric details comparable to those obtained from high-end capture devices, and outperform alternative approaches that require only a single unconstrained input image.

Abstract: We present an approach to infer a layer-structured 3D representation of a scene from a single input image. This allows us to infer not only the depth of the visible pixels, but also to capture the texture and depth for content in the scene that is not directly visible. We overcome the challenge posed by the lack of direct supervision by instead leveraging a more naturally available multi-view supervisory signal. Our insight is to use view synthesis as a proxy task: we enforce that our representation (inferred from a single image), when rendered from a novel perspective, matches the true observed image. We present a learning framework that operationalizes this insight using a new, differentiable novel view renderer. We provide qualitative and quantitative validation of our approach in two different settings, and demonstrate that we can learn to capture the hidden aspects of a scene. The project website can be found at https://shubhtuls.github.io/lsi/.

Abstract: We propose a material acquisition approach to recover the spatially-varying BRDF and normal map of a near-planar surface from a single image captured by a handheld mobile phone camera. Our method images the surface under arbitrary environment lighting with the flash turned on, thereby avoiding shadows while simultaneously capturing high-frequency specular highlights. We train a CNN to regress an SVBRDF and surface normals from this image. Our network is trained using a large-scale SVBRDF dataset and designed to incorporate physical insights for material estimation, including an in-network rendering layer to model appearance and a material classifier to provide additional supervision during training. We refine the results from the network using a dense CRF module whose terms are designed specifically for our task. The framework is trained end-to-end and produces high quality results for a variety of materials. We provide extensive ablation studies to evaluate our network on both synthetic and real data, while demonstrating significant improvements in comparisons with prior works.

Abstract: Layout is important for graphic design and scene generation. We propose a novel Generative Adversarial Network, called LayoutGAN, that synthesizes layouts by modeling geometric relations of different types of 2D elements. The generator of LayoutGAN takes as input a set of randomly-placed 2D graphic elements and uses self-attention modules to refine their labels and geometric parameters jointly to produce a realistic layout. Accurate alignment is critical for good layouts. We thus propose a novel differentiable wireframe rendering layer that maps the generated layout to a wireframe image, upon which a CNN-based discriminator is used to optimize the layouts in image space. We validate the effectiveness of LayoutGAN in various experiments including MNIST digit generation, document layout generation, clipart abstract scene generation and tangram graphic design.

Abstract: Recent progress in deep generative models has led to tremendous breakthroughs in image generation While being able to synthesize photorealistic images, existing models lack an understanding of our underlying 3D world Different from previous works built on 2D datasets and models, we present a new generative model, Visual Object Networks (VONs), synthesizing natural images of objects with a disentangled 3D representation Inspired by classic graphics rendering pipelines, we unravel the image formation process into three conditionally independent factors---shape, viewpoint, and texture---and present an end-to-end adversarial learning framework that jointly models 3D shape and 2D texture Our model first learns to synthesize 3D shapes that are indistinguishable from real shapes It then renders the object's 25D sketches (ie, silhouette and depth map) from its shape under a sampled viewpoint Finally, it learns to add realistic textures to these 25D sketches to generate realistic images The VON not only generates images that are more realistic than the state-of-the-art 2D image synthesis methods but also enables many 3D operations such as changing the viewpoint of a generated image, shape and texture editing, linear interpolation in texture and shape space, and transferring appearance across different objects and viewpoints

Abstract: We present a system for acquiring, processing, and rendering panoramic light field still photography for display in Virtual Reality (VR). We acquire spherical light field datasets with two novel light field camera rigs designed for portable and efficient light field acquisition. We introduce a novel real-time light field reconstruction algorithm that uses a per-view geometry and a disk-based blending field. We also demonstrate how to use a light field prefiltering operation to project from a high-quality offline reconstruction model into our real-time model while suppressing artifacts. We introduce a practical approach for compressing light fields by modifying the VP9 video codec to provide high quality compression with real-time, random access decompression.We combine these components into a complete light field system offering convenient acquisition, compact file size, and high-quality rendering while generating stereo views at 90Hz on commodity VR hardware. Using our system, we built a freely available light field experience application called Welcome to Light Fields featuring a library of panoramic light field stills for consumer VR which has been downloaded over 15,000 times.

Abstract: We propose to recover 3D shape structures from single RGB images, where structure refers to shape parts represented by cuboids and part relations encompassing connectivity and symmetry. Given a single 2D image with an object depicted, our goal is automatically recover a cuboid structure of the object parts as well as their mutual relations. We develop a convolutional-recursive auto-encoder comprised of structure parsing of a 2D image followed by structure recovering of a cuboid hierarchy. The encoder is achieved by a multi-scale convolutional network trained with the task of shape contour estimation, thereby learning to discern object structures in various forms and scales. The decoder fuses the features of the structure parsing network and the original image, and recursively decodes a hierarchy of cuboids. Since the decoder network is learned to recover part relations including connectivity and symmetry explicitly, the plausibility and generality of part structure recovery can be ensured. The two networks are jointly trained using the training data of contour-mask and cuboid-structure pairs. Such pairs are generated by rendering stock 3D CAD models coming with part segmentation. Our method achieves unprecedentedly faithful and detailed recovery of diverse 3D part structures from single-view 2D images. We demonstrate two applications of our method including structure-guided completion of 3D volumes reconstructed from single-view images and structure-aware interactive editing of 2D images.

Abstract: Dark silicon is pushing processor vendors to add more specialized units such as accelerators to commodity processor chips. Unfortunately this is done without enough care to security. In this paper we look at the security implications of integrated Graphical Processor Units (GPUs) found in almost all mobile processors. We demonstrate that GPUs, already widely employed to accelerate a variety of benign applications such as image rendering, can also be used to "accelerate" microarchitectural attacks (i.e., making them more effective) on commodity platforms. In particular, we show that an attacker can build all the necessary primitives for performing effective GPU-based microarchitectural attacks and that these primitives are all exposed to the web through standardized browser extensions, allowing side-channel and Rowhammer attacks from JavaScript. These attacks bypass state-of-the-art mitigations and advance existing CPU-based attacks: we show the first end-to-end microarchitectural compromise of a browser running on a mobile phone in under two minutes by orchestrating our GPU primitives. While powerful, these GPU primitives are not easy to implement due to undocumented hardware features. We describe novel reverse engineering techniques for peeking into the previously unknown cache architecture and replacement policy of the Adreno 330, an integrated GPU found in many common mobile platforms. This information is necessary when building shader programs implementing our GPU primitives. We conclude by discussing mitigations against GPU-enabled attackers.

Abstract: Motivated by augmented and virtual reality applications such as telepresence, there has been a recent focus in real-time performance capture of humans under motion. However, given the real-time constraint, these systems often suffer from artifacts in geometry and texture such as holes and noise in the final rendering, poor lighting, and low-resolution textures. We take the novel approach to augment such real-time performance capture systems with a deep architecture that takes a rendering from an arbitrary viewpoint, and jointly performs completion, super resolution, and denoising of the imagery in real-time. We call this approach neural (re-)rendering, and our live system "LookinGood". Our deep architecture is trained to produce high resolution and high quality images from a coarse rendering in real-time. First, we propose a self-supervised training method that does not require manual ground-truth annotation. We contribute a specialized reconstruction error that uses semantic information to focus on relevant parts of the subject, e.g. the face. We also introduce a salient reweighing scheme of the loss function that is able to discard outliers. We specifically design the system for virtual and augmented reality headsets where the consistency between the left and right eye plays a crucial role in the final user experience. Finally, we generate temporally stable results by explicitly minimizing the difference between two consecutive frames. We tested the proposed system in two different scenarios: one involving a single RGB-D sensor, and upper body reconstruction of an actor, the second consisting of full body 360° capture. Through extensive experimentation, we demonstrate how our system generalizes across unseen sequences and subjects.