OmnimatteRF: Robust Omnimatte with 3D Background Modeling

Video matting has broad applications, from adding interesting effects to casually captured movies to assisting video production professionals. Matting with associated effects such as shadows and reflections has also attracted increasing research activity, and methods like Omnimatte have been proposed to separate dynamic foreground objects of interest into their own layers. However, prior works represent video backgrounds as 2D image layers, limiting their capacity to express more complicated scenes, thus hindering application to real-world videos. In this paper, we propose a novel video matting method, OmnimatteRF, that combines dynamic 2D foreground layers and a 3D background model. The 2D layers preserve the details of the subjects, while the 3D background robustly reconstructs scenes in real-world videos. Extensive experiments demonstrate that our method reconstructs scenes with better quality on various videos.

Inverse Global Illumination using a Neural Radiometric Prior

Inverse rendering methods that account for global illumination are becoming more popular, but current methods require evaluating and automatically differentiating millions of path integrals by tracing multiple light bounces, which remains expensive and prone to noise. Instead, this paper proposes a radiometric prior as a simple alternative to building complete path integrals in a traditional differentiable path tracer, while still correctly accounting for global illumination. Inspired by the Neural Radiosity technique, we use a neural network as a radiance function, and we introduce a prior consisting of the norm of the residual of the rendering equation in the inverse rendering loss. We train our radiance network and optimize scene parameters simultaneously using a loss consisting of both a photometric term between renderings and the multi-view input images, and our radiometric prior (the residual term). This residual term enforces a physical constraint on the optimization that ensures that the radiance field accounts for global illumination. We compare our method to a vanilla differentiable path tracer, and more advanced techniques such as Path Replay Backpropagation. Despite the simplicity of our approach, we can recover scene parameters with comparable and in some cases better quality, at considerably lower computation times.

PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters

We propose PAniC-3D, a system to reconstruct stylized 3D character heads directly from illustrated (p)ortraits of (ani)me (c)haracters. Our anime-style domain poses unique challenges to single-view reconstruction; compared to natural images of human heads, character portrait illustrations have hair and accessories with more complex and diverse geometry, and are shaded with non-photorealistic contour lines. In addition, there is a lack of both 3D model and portrait illustration data suitable to train and evaluate this ambiguous stylized reconstruction task. Facing these challenges, our proposed PAniC-3D architecture crosses the illustration-to-3D domain gap with a line-filling model, and represents sophisticated geometries with a volumetric radiance field. We train our system with two large new datasets (11.2k Vroid 3D models, 1k Vtuber portrait illustrations), and evaluate on a novel AnimeRecon benchmark of illustration-to-3D pairs. PAniC-3D significantly outperforms baseline methods, and provides data to establish the task of stylized reconstruction from portrait illustrations.

Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

Surface reconstruction from point clouds is vital for 3D computer vision. State-of-the-art methods leverage large datasets to first learn local context priors that are represented as neural network-based signed distance functions (SDFs) with some parameters encoding the local contexts. To reconstruct a surface at a specific query location at inference time, these methods then match the local reconstruction target by searching for the best match in the local prior space (by optimizing the parameters encoding the local context) at the given query location. However, this requires the local context prior to generalize to a wide variety of unseen target regions, which is hard to achieve. To resolve this issue, we introduce Predictive Context Priors by learning Predictive Queries for each specific point cloud at inference time. Specifically, we first train a local context prior using a large point cloud dataset similar to previous techniques. For surface reconstruction at inference time, however, we specialize the local context prior into our Predictive Context Prior by learning Predictive Queries, which predict adjusted spatial query locations as displacements of the original locations. This leads to a global SDF that fits the specific point cloud the best. Intuitively, the query prediction enables us to flexibly search the learned local context prior over the entire prior space, rather than being restricted to the fixed query locations, and this improves the generalizability. Our method does not require ground truth signed distances, normals, or any additional procedure of signed distance fusion across overlapping regions. Our experimental results in surface reconstruction for single shapes or complex scenes show significant improvements over the state-of-the-art under widely used benchmarks.

Differentiable Neural Radiosity

We introduce Differentiable Neural Radiosity, a novel method of representing the solution of the differential rendering equation using a neural network. Inspired by neural radiosity techniques, we minimize the norm of the residual of the differential rendering equation to directly optimize our network. The network is capable of outputting continuous, view-independent gradients of the radiance field with respect to scene parameters, taking into account differential global illumination effects while keeping memory and time complexity constant in path length. To solve inverse rendering problems, we use a pre-trained instance of our network that represents the differential radiance field with respect to a limited number of scene parameters. In our experiments, we leverage this to achieve faster and more accurate convergence compared to other techniques such as Automatic Differentiation, Radiative Backpropagation, and Path Replay Backpropagation.

HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars

We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural Rendering (HVTR), which synthesizes virtual human avatars from arbitrary poses efficiently and at high quality. First, we learn to encode articulated human motions on a dense UV manifold of the human body surface. To handle complicated motions (e.g., self-occlusions), we then leverage the encoded information on the UV manifold to construct a 3D volumetric representation based on a dynamic pose-conditioned neural radiance field. While this allows us to represent 3D geometry with changing topology, volumetric rendering is computationally heavy. Hence we employ only a rough volumetric representation using a pose-conditioned downsampled neural radiance field (PD-NeRF), which we can render efficiently at low resolutions. In addition, we learn 2D textural features that are fused with rendered volumetric features in image space. The key advantage of our approach is that we can then convert the fused features into a high resolution, high-quality avatar by a fast GAN-based textural renderer. We demonstrate that hybrid rendering enables HVTR to handle complicated motions, render high-quality avatars under user-controlled poses/shapes and even loose clothing, and most importantly, be fast at inference time. Our experimental results also demonstrate state-of-the-art quantitative results.

Improving the Perceptual Quality of 2D Animation Interpolation

Traditional 2D animation is labor-intensive, often requiring animators to manually draw twelve illustrations per second of movement. While automatic frame interpolation may ease this burden, the artistic effects inherent to 2D animation make video synthesis particularly challenging compared to in the photorealistic domain. Lower framerates result in larger displacements and occlusions, discrete perceptual elements (e.g. lines and solid-color regions) pose difficulties for texture-oriented convolutional networks, and exaggerated nonlinear movements hinder training data collection. Previous work tried addressing these issues, but used unscalable methods and focused on pixel-perfect performance. In contrast, we build a scalable system more appropriately centered on perceptual quality for this artistic domain. Firstly, we propose a lightweight architecture with a simple yet effective occlusion-inpainting technique to improve convergence on perceptual metrics with fewer trainable parameters. Secondly, we design a novel auxiliary module that leverages the Euclidean distance transform to improve the preservation of key line and region structures. Thirdly, we automatically double the existing manually-collected dataset for this task by quantitatively filtering out movement nonlinearities, allowing us to improve model generalization. Finally, we establish LPIPS and chamfer distance as strongly preferable to PSNR and SSIM through a user study, validating our system's emphasis on perceptual quality in the 2D animation domain.

EgoRenderer: Rendering Human Avatars from Egocentric Camera Images

We present EgoRenderer, a system for rendering full-body neural avatars of a person captured by a wearable, egocentric fisheye camera that is mounted on a cap or a VR headset. Our system renders photorealistic novel views of the actor and her motion from arbitrary virtual camera locations. Rendering full-body avatars from such egocentric images come with unique challenges due to the top-down view and large distortions. We tackle these challenges by decomposing the rendering process into several steps, including texture synthesis, pose construction, and neural image translation. For texture synthesis, we propose Ego-DPNet, a neural network that infers dense correspondences between the input fisheye images and an underlying parametric body model, and to extract textures from egocentric inputs. In addition, to encode dynamic appearances, our approach also learns an implicit texture stack that captures detailed appearance variation across poses and viewpoints. For correct pose generation, we first estimate body pose from the egocentric view using a parametric model. We then synthesize an external free-viewpoint pose image by projecting the parametric model to the user-specified target viewpoint. We next combine the target pose image and the textures into a combined feature image, which is transformed into the output color image using a neural image translation network. Experimental evaluations show that EgoRenderer is capable of generating realistic free-viewpoint avatars of a person wearing an egocentric camera. Comparisons to several baselines demonstrate the advantages of our approach.

PatchGame: Learning to Signal Mid-level Patches in Referential Games

We study a referential game (a type of signaling game) where two agents communicate with each other via a discrete bottleneck to achieve a common goal. In our referential game, the goal of the speaker is to compose a message or a symbolic representation of "important" image patches, while the task for the listener is to match the speaker's message to a different view of the same image. We show that it is indeed possible for the two agents to develop a communication protocol without explicit or implicit supervision. We further investigate the developed protocol and show the applications in speeding up recent Vision Transformers by using only important patches, and as pre-training for downstream recognition tasks (e.g., classification). Code available at https://github.com/kampta/PatchGame.

Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching

Learning to generate 3D point clouds without 3D supervision is an important but challenging problem. Current solutions leverage various differentiable renderers to project the generated 3D point clouds onto a 2D image plane, and train deep neural networks using the per-pixel difference with 2D ground truth images. However, these solutions are still struggling to fully recover fine structures of 3D shapes, such as thin tubes or planes. To resolve this issue, we propose an unsupervised approach for 3D point cloud generation with fine structures. Specifically, we cast 3D point cloud learning as a 2D projection matching problem. Rather than using entire 2D silhouette images as a regular pixel supervision, we introduce structure adaptive sampling to randomly sample 2D points within the silhouettes as an irregular point supervision, which alleviates the consistency issue of sampling from different view angles. Our method pushes the neural network to generate a 3D point cloud whose 2D projections match the irregular point supervision from different view angles. Our 2D projection matching approach enables the neural network to learn more accurate structure information than using the per-pixel difference, especially for fine and thin 3D structures. Our method can recover fine 3D structures from 2D silhouette images at different resolutions, and is robust to different sampling methods and point number in irregular point supervision. Our method outperforms others under widely used benchmarks. Our code, data and models are available at https://github.com/chenchao15/2D\_projection\_matching.