SIGGRAPH 2022 论文列表

We, as human beings, can understand and picture a familiar scene from arbitrary viewpoints given a single image, whereas this is still a grand challenge for computers. We hereby present a novel solution to mimic such human perception capability based on a new paradigm of amodal 3D scene understanding with neural rendering for a closed scene. Specifically, we first learn the prior knowledge of the objects in a closed scene via an offline stage, which facilitates an online stage to understand the room with unseen furniture arrangement. During the online stage, given a panoramic image of the scene in different layouts, we utilize a holistic neural-rendering-based optimization framework to efficiently estimate the correct 3D scene layout and deliver realistic free-viewpoint rendering. In order to handle the domain gap between the offline and online stage, our method exploits compositional neural rendering techniques for data augmentation in the offline training. The experiments on both synthetic and real datasets demonstrate that our two-stage design achieves robust 3D scene understanding and outperforms competing methods by a large margin, and we also show that our realistic free-viewpoint rendering enables various applications, including scene touring and editing. Code and data are available on the project webpage: https://zju3dv.github.io/nr_in_a_room/.

Bidirectional reflectance distribution functions (BRDFs) are pervasively used in computer graphics to produce realistic physically-based appearance. Many common materials in the real world have more than one layer, like wood, skin, car paint, and many decorative materials. However, precise simulation of layered material optics is non-trivial. The most accurate approaches rely on Monte Carlo random walks to simulate the light transport within the layers, leading to high variance and cost. Other approaches are efficient, but less accurate. In this paper, we propose to perform layering in the neural space, by compressing BRDFs into latent codes via a proposed representation neural network, and performing a learned layering operation on these latent vectors via a layering network. Our BRDF evaluation is noise-free and computationally efficient, compared to the state-of-the-art approach; it is also a first step towards a “neural algebra” of operations on BRDFs in a latent space.

This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network, enabling training and evaluating over heterogeneous collections of meshes that do not share a triangulation, as well as producing highly detail-preserving maps whose accuracy exceeds current state of the art. The framework is based on reducing the neural aspect to a prediction of a matrix for a single given point, conditioned on a global shape descriptor. The field of matrices is then projected onto the tangent bundle of the given mesh, and used as candidate jacobians for the predicted map. The map is computed by a standard Poisson solve, implemented as a differentiable layer with cached pre-factorization for efficient training. This construction is agnostic to the triangulation of the input, thereby enabling applications on datasets with varying triangulations. At the same time, by operating in the intrinsic gradient domain of each individual mesh, it allows the framework to predict highly-accurate mappings. We validate these properties by conducting experiments over a broad range of scenarios, from semantic ones such as morphing, registration, and deformation transfer, to optimization-based ones, such as emulating elastic deformations and contact correction, as well as being the first work, to our knowledge, to tackle the task of learning to compute UV parameterizations of arbitrary meshes. The results exhibit the high accuracy of the method as well as its versatility, as it is readily applied to the above scenarios without any changes to the framework.

We introduce neural dual contouring (NDC), a new data-driven approach to mesh reconstruction based on dual contouring (DC). Like traditional DC, it produces exactly one vertex per grid cell and one quad for each grid edge intersection, a natural and efficient structure for reproducing sharp features. However, rather than computing vertex locations and edge crossings with hand-crafted functions that depend directly on difficult-to-obtain surface gradients, NDC uses a neural network to predict them. As a result, NDC can be trained to produce meshes from signed or unsigned distance fields, binary voxel grids, or point clouds (with or without normals); and it can produce open surfaces in cases where the input represents a sheet or partial surface. During experiments with five prominent datasets, we find that NDC, when trained on one of the datasets, generalizes well to the others. Furthermore, NDC provides better surface reconstruction accuracy, feature preservation, output complexity, triangle quality, and inference time in comparison to previous learned (e.g., neural marching cubes, convolutional occupancy networks) and traditional (e.g., Poisson) methods. Code and data are available at https://github.com/czq142857/NDC.

In this poster, we present a live 360° panoramic-video based empathic Mixed Reality (MR) collaboration system that shares various Near-Gaze non-verbal communication cues including gaze, hand pointing, gesturing, and heart rate visualisations in real-time. The preliminary results indicate that the interface with the partner’s communication cues visualised close to the gaze point allows users to focus without dividing attention to the collaborator’s physical body movements yet still effectively communicate. Shared gaze visualisations coupled with deictic languages are primarily used to affirm joint attention and mutual understanding, while hand pointing and gesturing are used as secondary. Our approach provides a new way to help enable effective remote collaboration through varied empathic communication visualisations and modalities which covers different task properties and spatial setups.

We present a novel method to acquire object representations from online image collections, capturing high-quality geometry and material properties of arbitrary objects from photographs with varying cameras, illumination, and backgrounds. This enables various object-centric rendering applications such as novel-view synthesis, relighting, and harmonized background composition from challenging in-the-wild input. Using a multi-stage approach extending neural radiance fields, we first infer the surface geometry and refine the coarsely estimated initial camera parameters, while leveraging coarse foreground object masks to improve the training efficiency and geometry quality. We also introduce a robust normal estimation technique which eliminates the effect of geometric noise while retaining crucial details. Lastly, we extract surface material properties and ambient illumination, represented in spherical harmonics with extensions that handle transient elements, e.g. sharp shadows. The union of these components results in a highly modular and efficient object acquisition framework. Extensive evaluations and comparisons demonstrate the advantages of our approach in capturing high-quality geometry and appearance properties useful for rendering applications.

In this paper, we present Neural Adaptive Tomography (NeAT), the first adaptive, hierarchical neural rendering pipeline for tomography. Through a combination of neural features with an adaptive explicit representation, we achieve reconstruction times far superior to existing neural inverse rendering methods. The adaptive explicit representation improves efficiency by facilitating empty space culling and concentrating samples in complex regions, while the neural features act as a neural regularizer for the 3D reconstruction. The NeAT framework is designed specifically for the tomographic setting, which consists only of semi-transparent volumetric scenes instead of opaque objects. In this setting, NeAT outperforms the quality of existing optimization-based tomography solvers while being substantially faster. https://github.com/darglein/NeAT

Emerging Metaverse applications demand reliable, accurate, and photorealistic reproductions of human hands to perform sophisticated operations as if in the physical world. While real human hand represents one of the most intricate coordination between bones, muscle, tendon, and skin, state-of-the-art techniques unanimously focus on modeling only the skeleton of the hand. In this paper, we present NIMBLE, a novel parametric hand model that includes the missing key components, bringing 3D hand model to a new level of realism. We first annotate muscles, bones and skins on the recent Magnetic Resonance Imaging hand (MRI-Hand) dataset [Li et al. 2021] and then register a volumetric template hand onto individual poses and subjects within the dataset. NIMBLE consists of 20 bones as triangular meshes, 7 muscle groups as tetrahedral meshes, and a skin mesh. Via iterative shape registration and parameter learning, it further produces shape blend shapes, pose blend shapes, and a joint regressor. We demonstrate applying NIMBLE to modeling, rendering, and visual inference tasks. By enforcing the inner bones and muscles to match anatomic and kinematic rules, NIMBLE can animate 3D hands to new poses at unprecedented realism. To model the appearance of skin, we further construct a photometric HandStage to acquire high-quality textures and normal maps to model wrinkles and palm print. Finally, NIMBLE also benefits learning-based hand pose and shape estimation by either synthesizing rich data or acting directly as a differentiable layer in the inference network.

Möbius transformations play an important role in both geometry and spherical image processing – they are the group of conformal automorphisms of 2D surfaces and the spherical equivalent of homographies. Here we present a novel, Möbius-equivariant spherical convolution operator which we call Möbius convolution; with it, we develop the foundations for Möbius-equivariant spherical CNNs. Our approach is based on the following observation: to achieve equivariance, we only need to consider the lower-dimensional subgroup which transforms the positions of points as seen in the frames of their neighbors. To efficiently compute Möbius convolutions at scale we derive an approximation of the action of the transformations on spherical filters, allowing us to compute our convolutions in the spectral domain with the fast Spherical Harmonic Transform. The resulting framework is flexible and descriptive, and we demonstrate its utility by achieving promising results in both shape classification and image segmentation tasks.

We present a simple, fast, and smooth scheme to approximate Algebraic Point Set Surfaces using non-compact kernels, which is particularly suited for filtering and reconstructing point sets presenting large missing parts. Our key idea is to consider a moving level-of-detail of the input point set which is adaptive w.r.t. to the evaluation location, just such as the samples weights are output sensitive in the traditional moving least squares scheme. We also introduce an adaptive progressive octree refinement scheme, driven by the resulting implicit surface, to properly capture the modeled geometry even far away from the input samples. Similarly to typical compactly-supported approximations, our operator runs in logarithmic time while defining high quality surfaces even on challenging inputs for which only global optimizations achieve reasonable results. We demonstrate our technique on a variety of point sets featuring geometric noise as well as large holes.

This article presents Motion Puzzle, a novel motion style transfer network that advances the state-of-the-art in several important respects. The Motion Puzzle is the first that can control the motion style of individual body parts, allowing for local style editing and significantly increasing the range of stylized motions. Designed to keep the human’s kinematic structure, our framework extracts style features from multiple style motions for different body parts and transfers them locally to the target body parts. Another major advantage is that it can transfer both global and local traits of motion style by integrating the adaptive instance normalization and attention modules while keeping the skeleton topology. Thus, it can capture styles exhibited by dynamic movements, such as flapping and staggering, significantly better than previous work. In addition, our framework allows for arbitrary motion style transfer without datasets with style labeling or motion pairing, making many publicly available motion datasets available for training. Our framework can be easily integrated with motion generation frameworks to create many applications, such as real-time motion transfer. We demonstrate the advantages of our framework with a number of examples and comparisons with previous work.

A non-Euclidean space is characterized as a manifold with a specific structure that violates Euclid's postulates. This paper proposes to approximate a manifold with polytopes. Based on the scene designer's specification, the polytopes are automatically concatenated and embedded in a higher-dimensional Euclidean space. Then, the scene is navigated and rendered via novel methods tailored to concatenated polytopes. The proof-of-concept implementation and experiments with it show that the proposed methods bring the virtual-world users unusual and fascinating experiences, which cannot be provided in Euclidean-space applications.

Recent research work has developed powerful generative models (e.g., StyleGAN2) that can synthesize complete human head images with impressive photorealism, enabling applications such as photorealistically editing real photographs. While these models can be trained on large collections of unposed images, their lack of explicit 3D knowledge makes it difficult to achieve even basic control over 3D viewpoint without unintentionally altering identity. On the other hand, recent Neural Radiance Field (NeRF) methods have already achieved multiview-consistent, photorealistic renderings but they are so far limited to a single facial identity. In this paper, we propose a new Morphable Radiance Field (MoRF) method that extends a NeRF into a generative neural model that can realistically synthesize multiview-consistent images of complete human heads, with variable and controllable identity. MoRF allows for morphing between particular identities, synthesizing arbitrary new identities, or quickly generating a NeRF from few images of a new subject, all while providing realistic and consistent rendering under novel viewpoints. We train MoRF in a supervised fashion by leveraging a high-quality database of multiview portrait images of several people, captured in studio with polarization-based separation of diffuse and specular reflection. Here, we demonstrate how MoRF is a strong new step forwards towards generative NeRFs for 3D neural head modeling.

In computational design and fabrication, neural networks are becoming important surrogates for bulky forward simulations. A long-standing, intertwined question is that of inverse design: how to compute a design that satisfies a desired target performance? Here, we show that the piecewise linear property, very common in everyday neural networks, allows for an inverse design formulation based on mixed-integer linear programming. Our mixed-integer inverse design uncovers globally optimal or near optimal solutions in a principled manner. Furthermore, our method significantly facilitates emerging, but challenging, combinatorial inverse design tasks, such as material selection. For problems where finding the optimal solution is intractable, we develop an efficient yet near-optimal hybrid approach. Eventually, our method is able to find solutions provably robust to possible fabrication perturbations among multiple designs with similar performances. Our code and data are available at https://gitlab.mpi-klsb.mpg.de/nansari/mixed-integer-neural-inverse-design.

We introduce MetaPo, a mobile robot with spheric display, 360° media I/O and robotic hands for creating a unified model of interspace communication. MetaPo works as a portal between pairs of physical-physical, cyber-cyber and cyber-physical spaces to provide 1) panoramic communication for multiple remote users, and 2) immersive interspace migration with mobility functionality. The paper overviews our concept and first prototype of MetaPo with its hardware and software implementation.

Procedural material graphs are a compact, parameteric, and resolution-independent representation that are a popular choice for material authoring. However, designing procedural materials requires significant expertise and publicly accessible libraries contain only a few thousand such graphs. We present MatFormer, a generative model that can produce a diverse set of high-quality procedural materials with complex spatial patterns and appearance. While procedural materials can be modeled as directed (operation) graphs, they contain arbitrary numbers of heterogeneous nodes with unstructured, often long-range node connections, and functional constraints on node parameters and connections. MatFormer addresses these challenges with a multi-stage transformer-based model that sequentially generates nodes, node parameters, and edges, while ensuring the semantic validity of the graph. In addition to generation, MatFormer can be used for the auto-completion and exploration of partial material graphs. We qualitatively and quantitatively demonstrate that our method outperforms alternative approaches, in both generated graph and material quality.

Many applications ranging from quasi-Monte Carlo integration over optimal control to neural networks benefit from high-dimensional, highly uniform samples. In the case of computer graphics, and more particularly in rendering, despite the need for uniformity, several sub-problems expose a low-dimensional structure. In this context, mastering sampling uniformity over projections while preserving high-dimensional uniformity has been intrinsically challenging. This difficulty may explain the relatively small number of mathematical constructions for such samplers. We propose a novel approach by showing that uniformity constraints can be expressed as an integer linear program that results in a sampler with the desired properties. As it turns out, complex constraints are easy to describe by means of stratification and sequence properties of digital nets. Formalized using generator matrix determinants, our new MatBuilder software solves the set of constraints by iterating the linear integer program solver in a greedy fashion to compute a problem-specific set of generator matrices that can be used as a drop-in replacement in the popular digital net samplers. The samplers created by MatBuilder achieve the uniformity of classic low discrepancy sequences. More importantly, we demonstrate the benefit of the unprecedented versatility of our constraint approach with respect to low-dimensional problem structure for several applications.