Despite the increasing popularity of avatar systems such as Snapchat Bitmojis, existing production avatar platforms face several limitations, such as a limited number of predefined assets, tedious customization processes, and inefficient rendering requirements. Addressing these shortcomings, we introduce Snapmoji, an avatar generation system that instantly creates 3D avatars, and enables customization in a process we call dual-stylization. Snapmoji first maps a selfie of a user to a primary avatar (e.g., Bitmoji style) using a new technique we name Gaussian Domain Adaptation (GDA), then applies a secondary style (e.g., skeleton, yarn, toy) to the primary avatar, all while preserving the user’s identity. The generated 3D avatars can then be rendered an animated on mobile devices at 30–40 FPS.

Bounded bihramonic weights are a popular tool used to rig and deform characters for animation, to compute reduced-order simulations, and to define feature descriptors for geometry processing. They necessitate tetrahedralizing the volume bounded by the surface, introducing the possibility of meshing artifacts or tetrahedralization failure. We introduce a mesh-free and robust automatic skinning technique that generates weights comparable to the current state of the art, but works reliably even on open surfaces, triangle soups, and point clouds where current methods fail. We achieve this through the use of a specialized Lagrangian representation enabled by the advent of hardware ray-tracing, which circumvents the need for finite elements while optimizing the biharmonic energy and enforcing boundary conditions. The flexibility of our formulation allows us to integrate artistic control through weight painting during the optimization. We offer a thorough qualitative and quantitative evaluation of our method.

This paper introduces FlowMap, an end-to-end differentiable method that solves for precise camera poses, cam-era intrinsics, and perframe dense depth of a video sequence. Our method performs per-video gradient-descent minimization of a simple least-squares objective that compares the optical flow induced by depth, intrinsics, and poses against correspondences obtained via off-the-shelf optical flow and point tracking. Alongside the use of point tracks to encourage long-term geometric consistency, we introduce differentiable re-parameterizations of depth, intrinsics, and pose that are amenable to first-order optimization. We empirically show that camera parameters and dense depth recovered by our method enable photo-realistic novel view synthesis on 360° trajectories using Gaussian Splatting. Our method not only far outperforms prior gradient-descent based bundle adjustment methods, but surprisingly approaches the accuracy of COLMAP, the state-of-the-art SfM method, on the downstream task of 360° novel view synthesis-even though our method is purely gradient-descent based, fully differentiable, and presents a complete departure from conventional SfM.

Classifier-free guidance (CFG) is a key technique for improving conditional generation in diffusion models, enabling more accurate control while enhancing sample quality. It is natural to extend this technique to video diffusion, which generates video conditioned on a variable number of context frames, collectively referred to as history. However, we find two key challenges to guiding with variable-length history: architectures that only support fixed-size conditioning, and the empirical observation that CFG-style history dropout performs poorly. To address this, we propose the Diffusion Forcing Transformer (DFoT), a video diffusion architecture and theoretically grounded training objective that jointly enable conditioning on a flexible number of history frames. We then introduce History Guidance, a family of guidance methods uniquely enabled by DFoT. We show that its simplest form, vanilla history guidance, already significantly improves video generation quality and temporal consistency. A more advanced method, history guidance across time and frequency further enhances motion dynamics, enables compositional generalization to out-of-distribution history, and can stably roll out extremely long videos. Project website: https://boyuan.space/history-guidance

The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods focus on synthesizing datasets that enable training randomly initialized models. In contrast, state-of-the-art vision approaches are increasingly building on large, pre-trained self-supervised models rather than training from scratch. In this paper, we investigate the problem of distilling datasets that enable us to optimally train linear probes on top of such large, pre-trained vision models. We introduce a method of dataset distillation for this task called Linear Gradient Matching that optimizes the synthetic images such that, when passed through a pre-trained feature extractor, they induce gradients in the linear classifier similar to those produced by the real data. Our method yields synthetic data that out-perform all real-image baselines and, remarkably, generalize across pre-trained vision models, enabling us, for instance, to train a linear CLIP probe that performs competitively using a dataset distilled via a DINO backbone. Further, we show that distilled datasets provide a valuable tool for model interpretability, predicting, among other things, how similar two model's representations spaces are under the platonic representation hypothesis or whether a model is sensitive to spurious correlations in adversarial datasets.

Recent work has shown that the generalization ability of image diffusion models arises from the locality properties of the trained neural network. In particular, when denoising a particular pixel, the model relies on a limited neighborhood of the input image around that pixel, which, according to the previous work, is tightly related to the ability of these models to produce novel images. Since locality is central to generalization, it is crucial to understand why diffusion models learn local behavior in the first place, as well as the factors that govern the properties of locality patterns. In this work, we present evidence that the locality in deep diffusion models emerges as a statistical property of the image dataset and is not due to the inductive bias of convolutional neural networks, as suggested in previous work. Specifically, we demonstrate that an optimal parametric linear denoiser exhibits similar locality properties to deep neural denoisers. We show, both theoretically and experimentally, that this locality arises directly from pixel correlations present in the image datasets. Moreover, locality patterns are drastically different on specialized datasets, approximating principal components of the data’s covariance. We use these insights to craft an analytical denoiser that better matches scores predicted by a deep diffusion model than prior expert-crafted alternatives. Our key takeaway is that while neural network architectures influence generation quality, their primary role is to capture locality patterns inherent in the data.

Impossible objects, geometric constructions that humans can perceive but that cannot exist in real life, have been a topic of intrigue in visual arts, perception, and graphics, yet no satisfying computer representation of such objects exists. Previous work embeds impossible objects in 3D, cutting them or twisting/bending them in the depth axis. Cutting an impossible object changes its local geometry at the cut, which can hamper downstream graphics applications, such as smoothing, while bending makes it difficult to relight the object. Both of these can invalidate geometry operations, such as distance computation. As an alternative, we introduce Meschers, meshes capable of representing impossible constructions akin to those found in M.C. Escher's woodcuts. Our representation has a theoretical foundation in discrete exterior calculus and supports the use-cases above, as we demonstrate in a number of example applications. Moreover, because we can do discrete geometry processing on our representation, we can inverse-render impossible objects. We also compare our representation to cut and bend representations of impossible objects.

We present Intrinsic Image Diffusion, a generative model for appearance decomposition of indoor scenes. Given a single input view, we sample multiple possible material ex-planations represented as albedo, roughness, and metal-lic maps. Appearance decomposition poses a considerable challenge in computer vision due to the inherent ambigu-ity between lighting and material properties and the lack of real datasets. To address this issue, we advocate for a probabilistic formulation, where instead of attempting to directly predict the true material properties, we employ a conditional generative model to sample from the solution space. Furthermore, we show that utilizing the strong learned prior of recent diffusion models trained on large-scale real-world images can be adapted to material estimation and highly improves the generalization to real images. Our method produces significantly sharper, more consis-tent, and more detailed materials, outperforming state-of-the-art methods by 1.5dB on PSNR and by 45% better FID score on albedo prediction. We demonstrate the effective-ness of our approach through experiments on both synthetic and real-world datasets.

We introduce pixelSplat, a feed-forward model that learns to reconstruct 3D radiance fields parameterized by 3D Gaussian primitives from pairs of images. Our model features real-time and memory-efficient rendering for scalable training as well as fast 3D reconstruction at inference time. To overcome local minima inherent to sparse and locally supported representations, we predict a dense probability distribution over 3D and sample Gaussian means from that probability distribution. We make this sampling operation differentiable via a reparameterization trick, allowing us to back-propagate gradients through the Gaussian splatting representation. We benchmark our method on wide-baseline novel view synthesis on the real-world RealEstate10k and ACID datasets, where we outperform state-of-the-art light field transformers and accelerate rendering by 2.5 orders of magnitude while reconstructing an interpretable and ed-itable 3D radiance field. Additional materials can be found on the project website.11dcharatan.github.io/pixelsplat

Robot co-design, where the morphology of a robot is optimized jointly with a learned policy to solve a specific task, is an emerging area of research. It holds particular promise for soft robots, which are amenable to novel manufacturing techniques that can realize learned morphologies and actuators. Inspired by nature and recent novel robot designs, we propose to go a step further and explore the novel reconfigurable robots, defined as robots that can change their morphology within their lifetime. We formalize control of reconfigurable soft robots as a high-dimensional reinforcement learning (RL) problem. We unify morphology change, locomotion, and environment interaction in the same action space, and introduce an appropriate, coarse-to-fine curriculum that enables us to discover policies that accomplish fine-grained control of the resulting robots. We also introduce DittoGym, a comprehensive RL benchmark for reconfigurable soft robots that require fine-grained morphology changes to accomplish the tasks. Finally, we evaluate our proposed coarse-to-fine algorithm on DittoGym, and demonstrate robots that learn to change their morphology several times within a sequence, uniquely enabled by our RL algorithm. More results are available at https://dittogym.github.io.

This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens without fully diffusing past ones. Our approach is shown to combine the strengths of next-token prediction models, such as variable-length generation, with the strengths of full-sequence diffusion models, such as the ability to guide sampling to desirable trajectories. Our method offers a range of additional capabilities, such as (1) rolling-out sequences of continuous tokens, such as video, with lengths past the training horizon, where baselines diverge and (2) new sampling and guiding schemes that uniquely profit from Diffusion Forcing's variable-horizon and causal architecture, and which lead to marked performance gains in decision-making and planning tasks. In addition to its empirical success, our method is proven to optimize a variational lower bound on the likelihoods of all subsequences of tokens drawn from the true joint distribution. Project website: https://boyuan.space/diffusion-forcing/

While 2D diffusion models generate realistic, high-detail images, 3D shape generation methods like Score Distillation Sampling (SDS) built on these 2D diffusion models produce cartoon-like, over-smoothed shapes. To help explain this discrepancy, we show that the image guidance used in Score Distillation can be understood as the velocity field of a 2D denoising generative process, up to the choice of a noise term. In particular, after a change of variables, SDS resembles a high-variance version of Denoising Diffusion Implicit Models (DDIM) with a differently-sampled noise term: SDS introduces noise i.i.d. randomly at each step, while DDIM infers it from the previous noise predictions. This excessive variance can lead to over-smoothing and unrealistic outputs. We show that a better noise approximation can be recovered by inverting DDIM in each SDS update step. This modification makes SDS's generative process for 2D images almost identical to DDIM. In 3D, it removes over-smoothing, preserves higher-frequency detail, and brings the generation quality closer to that of 2D samplers. Experimentally, our method achieves better or similar 3D generation quality compared to other state-of-the-art Score Distillation methods, all without training additional neural networks or multi-view supervision, and providing useful insights into relationship between 2D and 3D asset generation with diffusion models.

Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to a general-purpose latent space wherein encodings are related by isometries whenever their corresponding observations are geometrically related in world space. Specifically, we regularize the latent space such that maps between encodings preserve a learned inner product and commute with a learned functional operator, in the same manner as rigid-body transformations commute with the Laplacian. This approach forms an effective backbone for self-supervised representation learning, and we demonstrate that a simple off-the-shelf equivariant network operating in the pre-trained latent space can achieve results on par with meticulously-engineered, handcrafted networks designed to handle complex, nonlinear symmetries. Furthermore, isometric maps capture information about the respective transformations in world space, and we show that this allows us to regress camera poses directly from the coefficients of the maps between encodings of adjacent views of a scene.

We introduce a method for novel view synthesis given only a single wide-baseline stereo image pair. In this challenging regime, 3D scene points are regularly observed only once, requiring prior-based reconstruction of scene geometry and appearance. We find that existing approaches to novel view synthesis from sparse observations fail due to recovering incorrect 3D geometry and due to the high cost of differentiable rendering that precludes their scaling to large-scale training. We take a step towards resolving these shortcomings by formulating a multi-view transformer encoder, proposing an efficient, image-space epipolar line sampling scheme to assemble image features for a target ray, and a lightweight cross-attention-based renderer. Our contributions enable training of our method on a large-scale real-world dataset of indoor and outdoor scenes. We demonstrate that our method learns powerful multi-view geometry priors while reducing the rendering time. We conduct extensive comparisons on held-out test scenes across two real-world datasets, significantly outperforming prior work on novel view synthesis from sparse image observations and achieving multi-viewconsistent novel view synthesis.

Differentiable volumetric rendering is a powerful paradigm for 3D reconstruction and novel view synthesis. However, standard volume rendering approaches struggle with degenerate geometries in the case of limited viewpoint diversity, a common scenario in robotics applications. In this work, we propose to use the multi-view photometric objective from the self-supervised depth estimation literature as a geometric regularizer for volumetric rendering, significantly improving novel view synthesis without requiring additional information. Building upon this insight, we explore the explicit modeling of scene geometry using a generalist Transformer, jointly learning a radiance field as well as depth and light fields with a set of shared latent codes. We demonstrate that sharing geometric information across tasks is mutually beneficial, leading to improvements over single-task learning without an increase in network complexity. Our DeLiRa architecture achieves state-of-the-art results on the ScanNet benchmark, enabling high quality volumetric rendering as well as real-time novel view and depth synthesis in the limited viewpoint diversity setting. Our project page is https://sites.google.com/view/tri-delira.

Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their dependence on precise camera poses from structure-from-motion, which is prohibitively expensive to run at scale. We propose a method that jointly reconstructs camera poses and 3D neural scene representations online and in a single forward pass. We estimate poses by first lifting frame-to-frame optical flow to 3D scene flow via differentiable rendering, preserving locality and shift-equivariance of the image processing backbone. SE(3) camera pose estimation is then performed via a weighted least-squares fit to the scene flow field. This formulation enables us to jointly supervise pose estimation and a generalizable neural scene representation via re-rendering the input video, and thus, train end-to-end and fully self-supervised on real-world video datasets. We demonstrate that our method performs robustly on diverse, real-world video, notably on sequences traditionally challenging to optimization-based pose estimation techniques.

Denoising diffusion models are a powerful type of generative models used to capture complex distributions of real-world signals. However, their applicability is limited to scenarios where training samples are readily available, which is not always the case in real-world applications. For example, in inverse graphics, the goal is to generate samples from a distribution of 3D scenes that align with a given image, but ground-truth 3D scenes are unavailable and only 2D images are accessible. To address this limitation, we propose a novel class of denoising diffusion probabilistic models that learn to sample from distributions of signals that are never directly observed. Instead, these signals are measured indirectly through a known differentiable forward model, which produces partial observations of the unknown signal. Our approach involves integrating the forward model directly into the denoising process. A key contribution of our work is the integration of a differentiable forward model into the denoising process. This integration effectively connects the generative modeling of observations with the generative modeling of the underlying signals, allowing for end-to-end training of a conditional generative model over signals. During inference, our approach enables sampling from the distribution of underlying signals that are consistent with a given partial observation. We demonstrate the effectiveness of our method on three challenging computer vision tasks. For instance, in the context of inverse graphics, our model enables direct sampling from the distribution of 3D scenes that align with a single 2D input image.

We propose a variational technique to optimize for generalized barycentric coordinates that offers additional control compared to existing models. Prior work represents barycentric coordinates using meshes or closed-form formulae, in practice limiting the choice of objective function. In contrast, we directly parameterize the continuous function that maps any coordinate in a polytope's interior to its barycentric coordinates using a neural field. This formulation is enabled by our theoretical characterization of barycentric coordinates, which allows us to construct neural fields that parameterize the entire function class of valid coordinates. We demonstrate the flexibility of our model using a variety of objective functions, including multiple smoothness and deformation-aware energies; as a side contribution, we also present mathematically-justified means of measuring and minimizing objectives like total variation on discontinuous neural fields. We offer a practical acceleration strategy, present a thorough validation of our algorithm, and demonstrate several applications.

Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details. But collecting, processing and annotating real data at scale is difficult, expensive, and frequently raises additional privacy, fairness and legal concerns. Synthetic data is a powerful tool with the potential to address these shortcomings: 1) it is cheap 2) supports rich ground-truth annotations 3) offers full control over data and 4) can circumvent or mitigate problems regarding bias, privacy and licensing. Unfortunately, software tools for effective data generation are less mature than those for architecture design and training, which leads to fragmented generation efforts. To address these problems we introduce Kubric, an open-source Python framework that interfaces with PyBullet and Blender to generate photo-realistic scenes, with rich annotations, and seamlessly scales to large jobs distributed over thousands of machines, and generating TBs of data. We demonstrate the effectiveness of Kubric by presenting a series of 13 different generated datasets for tasks ranging from studying 3D NeRF models to optical flow estimation. We release Kubric, the used assets, all of the generation code, as well as the rendered datasets for reuse and modification.

We present Neural Descriptor Fields (NDFs), an object representation that encodes both points and relative poses between an object and a target (such as a robot gripper or a rack used for hanging) via category-level descriptors. We employ this representation for object manipulation, where given a task demonstration, we want to repeat the same task on a new object instance from the same category. We propose to achieve this objective by searching (via optimization) for the pose whose descriptor matches that observed in the demonstration. NDFs are conveniently trained in a self-supervised fashion via a 3D auto-encoding task that does not rely on expert-labeled keypoints. Further, NDFs are SE(3)-equivariant, guaranteeing performance that generalizes across all possible 3D object translations and rotations. We demonstrate learning of manipulation tasks from few (∼5-10) demonstrations both in simulation and on a real robot. Our performance generalizes across both object instances and 6-DoF object poses, and significantly outperforms a recent baseline that relies on 2D descriptors. Project website: https://yilundu.github.io/ndf/

Emerging neural radiance fields (NeRF) are a promising scene representation for computer graphics, enabling high-quality 3D reconstruction and novel view synthesis from image observations.However, editing a scene represented by a NeRF is challenging, as the underlying connectionist representations such as MLPs or voxel grids are not object-centric or compositional.In particular, it has been difficult to selectively edit specific regions or objects.In this work, we tackle the problem of semantic scene decomposition of NeRFs to enable query-based local editing of the represented 3D scenes.We propose to distill the knowledge of off-the-shelf, self-supervised 2D image feature extractors such as CLIP-LSeg or DINO into a 3D feature field optimized in parallel to the radiance field.Given a user-specified query of various modalities such as text, an image patch, or a point-and-click selection, 3D feature fields semantically decompose 3D space without the need for re-training, and enables us to semantically select and edit regions in the radiance field.Our experiments validate that the distilled feature fields can transfer recent progress in 2D vision and language foundation models to 3D scene representations, enabling convincing 3D segmentation and selective editing of emerging neural graphics representations.

Abstract Synthesizing photo‐realistic images and videos is at the heart of computer graphics and has been the focus of decades of research. Traditionally, synthetic images of a scene are generated using rendering algorithms such as rasterization or ray tracing, which take specifically defined representations of geometry and material properties as input. Collectively, these inputs define the actual scene and what is rendered, and are referred to as the scene representation (where a scene consists of one or more objects). Example scene representations are triangle meshes with accompanied textures (e.g., created by an artist), point clouds (e.g., from a depth sensor), volumetric grids (e.g., from a CT scan), or implicit surface functions (e.g., truncated signed distance fields). The reconstruction of such a scene representation from observations using differentiable rendering losses is known as inverse graphics or inverse rendering. Neural rendering is closely related, and combines ideas from classical computer graphics and machine learning to create algorithms for synthesizing images from real‐world observations. Neural rendering is a leap forward towards the goal of synthesizing photo‐realistic image and video content. In recent years, we have seen immense progress in this field through hundreds of publications that show different ways to inject learnable components into the rendering pipeline. This state‐of‐the‐art report on advances in neural rendering focuses on methods that combine classical rendering principles with learned 3D scene representations, often now referred to as neural scene representations. A key advantage of these methods is that they are 3D‐consistent by design, enabling applications such as novel viewpoint synthesis of a captured scene. In addition to methods that handle static scenes, we cover neural scene representations for modeling non‐rigidly deforming objects and scene editing and composition. While most of these approaches are scene‐specific, we also discuss techniques that generalize across object classes and can be used for generative tasks. In addition to reviewing these state‐of‐the‐art methods, we provide an overview of fundamental concepts and definitions used in the current literature. We conclude with a discussion on open challenges and social implications.

Abstract Recent advances in machine learning have led to increased interest in solving visual computing problems using methods that employ coordinate‐based neural networks. These methods, which we call neural fields , parameterize physical properties of scenes or objects across space and time. They have seen widespread success in problems such as 3D shape and image synthesis, animation of human bodies, 3D reconstruction, and pose estimation. Rapid progress has led to numerous papers, but a consolidation of the discovered knowledge has not yet emerged. We provide context, mathematical grounding, and a review of over 250 papers in the literature on neural fields. In Part I , we focus on neural field techniques by identifying common components of neural field methods, including different conditioning, representation, forward map, architecture, and manipulation methods. In Part II , we focus on applications of neural fields to different problems in visual computing, and beyond (e.g., robotics, audio). Our review shows the breadth of topics already covered in visual computing, both historically and in current incarnations, and highlights the improved quality, flexibility, and capability brought by neural field methods. Finally, we present a companion website that acts as a living database that can be continually updated by the community.

Deep neural networks have been used widely to learn the latent structure of datasets, across modalities such as images, shapes, and audio signals. However, existing models are generally modality-dependent, requiring custom architectures and objectives to process different classes of signals. We leverage neural fields to capture the underlying structure in image, shape, audio and cross-modal audiovisual domains in a modality-independent manner. We cast our task as one of learning a manifold, where we aim to infer a low-dimensional, locally linear subspace in which our data resides. By enforcing coverage of the manifold, local linearity, and local isometry, our model -- dubbed GEM -- learns to capture the underlying structure of datasets across modalities. We can then travel along linear regions of our manifold to obtain perceptually consistent interpolations between samples, and can further use GEM to recover points on our manifold and glean not only diverse completions of input images, but cross-modal hallucinations of audio or image signals. Finally, we show that by walking across the underlying manifold of GEM, we may generate new samples in our signal domains.

Inferring representations of 3D scenes from 2D observations is a fundamental problem of computer graphics, computer vision, and artificial intelligence. Emerging 3D-structured neural scene representations are a promising approach to 3D scene understanding. In this work, we propose a novel neural scene representation, Light Field Networks or LFNs, which represent both geometry and appearance of the underlying 3D scene in a 360-degree, four-dimensional light field parameterized via a neural implicit representation. Rendering a ray from an LFN requires only a single network evaluation, as opposed to hundreds of evaluations per ray for ray-marching or volumetric based renderers in 3D-structured neural scene representations. In the setting of simple scenes, we leverage meta-learning to learn a prior over LFNs that enables multi-view consistent light field reconstruction from as little as a single image observation. This results in dramatic reductions in time and memory complexity, and enables real-time rendering. The cost of storing a 360-degree light field via an LFN is two orders of magnitude lower than conventional methods such as the Lumigraph. Utilizing the analytical differentiability of neural implicit representations and a novel parameterization of light space, we further demonstrate the extraction of sparse depth maps from LFNs.

Real-world, imaging systems acquire measurements that are degraded by noise, optical aberrations, and other imperfections that make image processing for human viewing and higher-level perception tasks challenging. Conventional cameras address this problem by compartmentalizing imaging from high-level task processing. As such, conventional imaging involves processing the RAW sensor measurements in a sequential pipeline of steps, such as demosaicking, denoising, deblurring, tone-mapping, and compression. This pipeline is optimized to obtain a visually pleasing image. High-level processing, however, involves steps such as feature extraction, classification, tracking, and fusion. While this silo-ed design approach allows for efficient development, it also dictates compartmentalized performance metrics without knowledge of the higher-level task of the camera system. For example, today’s demosaicking and denoising algorithms are designed using perceptual image quality metrics but not with domain-specific tasks such as object detection in mind. We propose an end-to-end differentiable architecture that jointly performs demosaicking, denoising, deblurring, tone-mapping, and classification (see Figure 1). The architecture does not require any intermediate losses based on perceived image quality and learns processing pipelines whose outputs differ from those of existing ISPs optimized for perceptual quality, preserving fine detail at the cost of increased noise and artifacts. We show that state-of-the-art ISPs discard information that is essential in corner cases, such as extremely low-light conditions, where conventional imaging and perception stacks fail. We demonstrate on captured and simulated data that our model substantially improves perception in low light and other challenging conditions, which is imperative for real-world applications such as autonomous driving, robotics, and surveillance. Finally, we found that the proposed model also achieves state-of-the-art accuracy when optimized for image reconstruction in low-light conditions, validating the architecture itself as a potentially useful drop-in network for reconstruction and analysis tasks beyond the applications demonstrated in this work. Our proposed models, datasets, and calibration data are available at https://github.com/princeton-computational-imaging/DirtyPixels .

The recent success of implicit neural scene representations has presented a viable new method for how we capture and store 3D scenes. Unlike conventional 3D representations, such as point clouds, which explicitly store scene properties in discrete, localized units, these implicit representations encode a scene in the weights of a neural network which can be queried at any coordinate to produce these same scene properties. Thus far, implicit representations have primarily been optimized to estimate only the appearance and/or 3D geometry information in a scene. We take the next step and demonstrate that an existing implicit representation (SRNs) [67] is actually multi-modal; it can be further leveraged to perform per-point semantic segmentation while retaining its ability to represent appearance and geometry. To achieve this multi-modal behavior, we utilize a semi-supervised learning strategy atop the existing pre-trained scene representation. Our method is simple, general, and only requires a few tens of labeled 2D segmentation masks in order to achieve dense 3D semantic segmentation. We explore two novel applications for this semantically aware implicit neural scene representation: 3D novel view and semantic label synthesis given only a single input RGB image or 2D label mask, as well as 3D interpolation of appearance and semantics.

Neural implicit shape representations are an emerging paradigm that offers many potential benefits over conventional discrete representations, including memory efficiency at a high spatial resolution. Generalizing across shapes with such neural implicit representations amounts to learning priors over the respective function space and enables geometry reconstruction from partial or noisy observations. Existing generalization methods rely on conditioning a neural network on a low-dimensional latent code that is either regressed by an encoder or jointly optimized in the auto-decoder framework. Here, we formalize learning of a shape space as a meta-learning problem and leverage gradient-based meta-learning algorithms to solve this task. We demonstrate that this approach performs on par with auto-decoder based approaches while being an order of magnitude faster at test-time inference. We further demonstrate that the proposed gradient-based method outperforms encoder-decoder based methods that leverage pooling-based set encoders.

Implicitly defined, continuous, differentiable signal representations parameterized by neural networks have emerged as a powerful paradigm, offering many possible benefits over conventional representations. However, current network architectures for such implicit neural representations are incapable of modeling signals with fine detail, and fail to represent a signal's spatial and temporal derivatives, despite the fact that these are essential to many physical signals defined implicitly as the solution to partial differential equations. We propose to leverage periodic activation functions for implicit neural representations and demonstrate that these networks, dubbed sinusoidal representation networks or SIRENs, are ideally suited for representing complex natural signals and their derivatives. We analyze SIREN activation statistics to propose a principled initialization scheme and demonstrate the representation of images, wavefields, video, sound, and their derivatives. Further, we show how SIRENs can be leveraged to solve challenging boundary value problems, such as particular Eikonal equations (yielding signed distance functions), the Poisson equation, and the Helmholtz and wave equations. Lastly, we combine SIRENs with hypernetworks to learn priors over the space of SIREN functions.

Abstract Efficient rendering of photo‐realistic virtual worlds is a long standing effort of computer graphics. Modern graphics techniques have succeeded in synthesizing photo‐realistic images from hand‐crafted scene representations. However, the automatic generation of shape, materials, lighting, and other aspects of scenes remains a challenging problem that, if solved, would make photo‐realistic computer graphics more widely accessible. Concurrently, progress in computer vision and machine learning have given rise to a new approach to image synthesis and editing, namely deep generative models. Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e.g., by the integration of differentiable rendering into network training. With a plethora of applications in computer graphics and vision, neural rendering is poised to become a new area in the graphics community, yet no survey of this emerging field exists. This state‐of‐the‐art report summarizes the recent trends and applications of neural rendering. We focus on approaches that combine classic computer graphics techniques with deep generative models to obtain controllable and photorealistic outputs. Starting with an overview of the underlying computer graphics and machine learning concepts, we discuss critical aspects of neural rendering approaches. Specifically, our emphasis is on the type of control, i.e., how the control is provided, which parts of the pipeline are learned, explicit vs. implicit control, generalization, and stochastic vs. deterministic synthesis. The second half of this state‐of‐the‐art report is focused on the many important use cases for the described algorithms such as novel view synthesis, semantic photo manipulation, facial and body reenactment, relighting, free‐viewpoint video, and the creation of photo‐realistic avatars for virtual and augmented reality telepresence. Finally, we conclude with a discussion of the social implications of such technology and investigate open research problems.

In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis. To this end, we propose DeepVoxels, a learned representation that encodes the view-dependent appearance of a 3D scene without having to explicitly model its geometry. At its core, our approach is based on a Cartesian 3D grid of persistent embedded features that learn to make use of the underlying 3D scene structure. Our approach combines insights from 3D geometric computer vision with recent advances in learning image-to-image mappings based on adversarial loss functions. DeepVoxels is supervised, without requiring a 3D reconstruction of the scene, using a 2D re-rendering loss and enforces perspective and multi-view geometry in a principled manner. We apply our persistent 3D scene representation to the problem of novel view synthesis demonstrating high-quality results for a variety of challenging scenes.

Unsupervised learning with generative models has the potential of discovering rich representations of 3D scenes. While geometric deep learning has explored 3D-structure-aware representations of scene geometry, these models typically require explicit 3D supervision. Emerging neural scene representations can be trained only with posed 2D images, but existing methods ignore the three-dimensional structure of scenes. We propose Scene Representation Networks (SRNs), a continuous, 3D-structure-aware scene representation that encodes both geometry and appearance. SRNs represent scenes as continuous functions that map world coordinates to a feature representation of local scene properties. By formulating the image formation as a differentiable ray-marching algorithm, SRNs can be trained end-to-end from only 2D images and their camera poses, without access to depth or shape. This formulation naturally generalizes across scenes, learning powerful geometry and appearance priors in the process. We demonstrate the potential of SRNs by evaluating them for novel view synthesis, few-shot reconstruction, joint shape and appearance interpolation, and unsupervised discovery of a non-rigid face model.

In typical cameras the optical system is designed first; once it is fixed, the parameters in the image processing algorithm are tuned to get good image reproduction. In contrast to this sequential design approach, we consider joint optimization of an optical system (for example, the physical shape of the lens) together with the parameters of the reconstruction algorithm. We build a fully-differentiable simulation model that maps the true source image to the reconstructed one. The model includes diffractive light propagation, depth and wavelength-dependent effects, noise and nonlinearities, and the image post-processing. We jointly optimize the optical parameters and the image processing algorithm parameters so as to minimize the deviation between the true and reconstructed image, over a large set of images. We implement our joint optimization method using autodifferentiation to efficiently compute parameter gradients in a stochastic optimization algorithm. We demonstrate the efficacy of this approach by applying it to achromatic extended depth of field and snapshot super-resolution imaging.

Virtual reality systems are widely believed to be the next major computing platform. There are, however, some barriers to adoption that must be addressed, such as that of motion sickness - which can lead to undesirable symptoms including postural instability, headaches, and nausea. Motion sickness in virtual reality occurs as a result of moving visual stimuli that cause users to perceive self-motion while they remain stationary in the real world. There are several contributing factors to both this perception of motion and the subsequent onset of sickness, including field of view, motion velocity, and stimulus depth. We verify first that differences in vection due to relative stimulus depth remain correlated with sickness. Then, we build a dataset of stereoscopic 3D videos and their corresponding sickness ratings in order to quantify their nauseogenicity, which we make available for future use. Using this dataset, we train a machine learning algorithm on hand-crafted features (quantifying speed, direction, and depth as functions of time) from each video, learning the contributions of these various features to the sickness ratings. Our predictor generally outperforms a naïve estimate, but is ultimately limited by the size of the dataset. However, our result is promising and opens the door to future work with more extensive datasets. This and further advances in this space have the potential to alleviate developer and end user concerns about motion sickness in the increasingly commonplace virtual world.

Understanding how people explore immersive virtual environments is crucial for many applications, such as designing virtual reality (VR) content, developing new compression algorithms, or learning computational models of saliency or visual attention. Whereas a body of recent work has focused on modeling saliency in desktop viewing conditions, VR is very different from these conditions in that viewing behavior is governed by stereoscopic vision and by the complex interaction of head orientation, gaze, and other kinematic constraints. To further our understanding of viewing behavior and saliency in VR, we capture and analyze gaze and head orientation data of 169 users exploring stereoscopic, static omni-directional panoramas, for a total of 1980 head and gaze trajectories for three different viewing conditions. We provide a thorough analysis of our data, which leads to several important insights, such as the existence of a particular fixation bias, which we then use to adapt existing saliency predictors to immersive VR conditions. In addition, we explore other applications of our data and analysis, including automatic alignment of VR video cuts, panorama thumbnails, panorama video synopsis, and saliency-basedcompression.

Traditional cinematography has relied for over a century on a well-established set of editing rules, called continuity editing, to create a sense of situational continuity. Despite massive changes in visual content across cuts, viewers in general experience no trouble perceiving the discontinuous flow of information as a coherent set of events. However, Virtual Reality (VR) movies are intrinsically different from traditional movies in that the viewer controls the camera orientation at all times. As a consequence, common editing techniques that rely on camera orientations, zooms, etc., cannot be used. In this paper we investigate key relevant questions to understand how well traditional movie editing carries over to VR, such as: Does the perception of continuity hold across edit boundaries? Under which conditions? Does viewers' observational behavior change after the cuts? To do so, we rely on recent cognition studies and the event segmentation theory, which states that our brains segment continuous actions into a series of discrete, meaningful events. We first replicate one of these studies to assess whether the predictions of such theory can be applied to VR. We next gather gaze data from viewers watching VR videos containing different edits with varying parameters, and provide the first systematic analysis of viewers' behavior and the perception of continuity in VR. From this analysis we make a series of relevant findings; for instance, our data suggests that predictions from the cognitive event segmentation theory are useful guides for VR editing; that different types of edits are equally well understood in terms of continuity; and that spatial misalignments between regions of interest at the edit boundaries favor a more exploratory behavior even after viewers have fixated on a new region of interest. In addition, we propose a number of metrics to describe viewers' attentional behavior in VR. We believe the insights derived from our work can be useful as guidelines for VR content creation.