ACM Transactions on Graphics最新文献

Recently, Deep Learning-based methods for inverse tone mapping standard dynamic range (SDR) images to obtain high dynamic range (HDR) images have become very popular. These methods manage to fill over-exposed areas convincingly both in terms of details and dynamic range. To be effective, deep learning-based methods need to learn from large datasets and transfer this knowledge to the network weights. In this work, we tackle this problem from a completely different perspective. What can we learn from a single SDR 8-bit video? With the presented self-supervised approach, we show that, in many cases, a single SDR video is sufficient to generate an HDR video of the same quality or better than other state-of-the-art methods.

Barrier functions are crucial for maintaining an intersection and inversion free simulation trajectory but existing methods which directly use distance can restrict implementation design and performance. We present an approach to rewriting the barrier function for arriving at an efficient and robust approximation of its Hessian. The key idea is to formulate a simplicial geometric measure of contact using mesh boundary elements, from which analytic eigensystems are derived and enhanced with filtering and stiffening terms that ensure robustness with respect to the convergence of a Project-Newton solver. A further advantage of our rewriting of the barrier function is that it naturally caters to the notorious case of nearly-parallel edge-edge contacts for which we also present a novel analytic eigensystem. Our approach is thus well suited for standard second order unconstrained optimization strategies for resolving contacts, minimizing nonlinear nonconvex functions where the Hessian may be indefinite. The efficiency of our eigensystems alone yields a 3 × speedup over the standard IPC barrier formulation. We further apply our analytic proxy eigensystems to produce an entirely GPU-based implementation of IPC with significant further acceleration.

We present a comprehensive analysis of total variation (TV) on non-Euclidean domains and its eigenfunctions. We specifically address parameterized surfaces, a natural representation of the shapes used in 3D graphics. Our work sheds new light on the celebrated Beltrami and Anisotropic TV flows, and explains experimental findings from recent years on shape spectral TV [Fumero et al. 2020] and adaptive anisotropic spectral TV [Biton and Gilboa 2022]. A new notion of convexity on surfaces is derived by characterizing structures that are stable throughout the TV flow, performed on surfaces. We establish and numerically demonstrate quantitative relationships between TV, area, eigenvalue, and eigenfunctions of the TV operator on surfaces. Moreover, we expand the shape spectral TV toolkit to include zero-homogeneous flows, leading to efficient and versatile shape processing methods. These methods are exemplified through applications in smoothing, enhancement, and exaggeration filters. We introduce a novel method which, for the first time, addresses the shape deformation task using TV. This deformation technique is characterized by the concentration of deformation along geometrical bottlenecks, shown to coincide with the discontinuities of eigenfunctions. Overall, our findings elucidate recent experimental observations in spectral TV, provide a diverse framework for shape filtering, and present the first TV-based approach to shape deformation.

We introduce NeuralVDB, which improves on an existing industry standard for efficient storage of sparse volumetric data, denoted VDB [Museth 2013], by leveraging recent advancements in machine learning. Our novel hybrid data structure can reduce the memory footprints of VDB volumes by orders of magnitude, while maintaining its flexibility and only incurring small (user-controlled) compression errors. Specifically, NeuralVDB replaces the lower nodes of a shallow and wide VDB tree structure with multiple hierarchical neural networks that separately encode topology and value information by means of neural classifiers and regressors respectively. This approach is proven to maximize the compression ratio while maintaining the spatial adaptivity offered by the higher-level VDB data structure. For sparse signed distance fields and density volumes, we have observed compression ratios on the order of 10 × to more than 100 × from already compressed VDB inputs, with little to no visual artifacts. Furthermore, NeuralVDB is shown to offer more effective compression performance compared to other neural representations such as Neural Geometric Level of Detail [Takikawa et al. 2021], Variable Bitrate Neural Fields [Takikawa et al. 2022a], and Instant Neural Graphics Primitives [Müller et al. 2022]. Finally, we demonstrate how warm-starting from previous frames can accelerate training, i.e., compression, of animated volumes as well as improve temporal coherency of model inference, i.e., decompression.

The creation of truly believable simulated natural environments remains an unsolved problem in Computer Graphics. This is, in part, due to a lack of visual variety. In nature, apart from variation due to abiotic and biotic growth factors, a significant role is played by disturbance events, such as fires, windstorms, disease, and death and decay processes, which give rise to both standing dead trees (snags) and downed woody debris (logs). For instance, snags constitute on average (10% ) of unmanaged forests by basal area, and logs account for (2 frac{1}{2} ) times this quantity.

While previous systems have incorporated individual elements of disturbance (e.g., forest fires) and decay (e.g., the formation of humus), there has been no unifying treatment, perhaps because of the challenge of matching simulation results with generated geometric models.

In this paper, we present a framework that combines an ecosystem simulation, which explicitly incorporates disturbance events and decay processes, with a model realization process, which balances the uniqueness arising from life history with the need for instancing due to memory constraints. We tested our hypothesis concerning the visual impact of disturbance and decay with a two-alternative forced-choice experiment (n = 116). Our findings are that the presence of dead wood in various forms, as snags or logs, significantly improves the believability of natural scenes, while, surprisingly, general variation in the number of model instances, with up to 8 models per species, and a focus on disturbance events, does not.

An Escher-like tiling is a tiling consisting of one or a few artistic shapes of tile. This paper proposes a method for generating Escher-like tilings consisting of two distinct shapes (dihedral Escher-like tilings) that are as similar as possible to the two goal shapes specified by the user. This study is an extension of a previous study that successfully generated Escher-like tilings consisting of a single tile shape for a single goal shape. Building upon the previous study, our method attempts to exhaustively search for which parts of the discretized tile contours are adjacent to each other to form a tiling. For each configuration, two tile shapes are optimized to be similar to the given two goal shapes. By evaluating the similarity based on as-rigid-as possible deformation energy, the optimized tile shapes preserve the local structures of the goal shapes, even if substantial deformations are necessary to form a tiling. However, in the dihedral case, this approach is seemingly unrealistic because it suffers from the complexity of the energy function and the combinatorial explosion of the possible configurations. We developed a method to address these issues and show that the proposed algorithms can generate satisfactory dihedral Escher-like tilings in a realistic computation time, even for somewhat complex goal shapes.

Recent years have witnessed the rapid deployment of numerous physics-based modeling and simulation algorithms and techniques for fluids, solids, and their delicate coupling in computer animation. However, it still remains a challenging problem to model the complex elastic-viscoplastic (EVP) behaviors during fluid-solid phase transitions and facilitate their seamless interactions inside the same framework. In this paper, we propose a practical method capable of simulating granular flows, viscoplastic liquids, elastic-plastic solids, rigid bodies, and interacting with each other, to support novel phenomena all heavily involving realistic phase transitions, including dissolution, melting, cooling, expansion, shrinking, etc. At the physics level, we propose to combine and morph von Mises with Drucker-Prager and Cam-Clay yield models to establish a unified phase-field-driven EVP model, capable of describing the behaviors of granular, elastic, plastic, viscous materials, liquid, non-Newtonian fluids, and their smooth evolution. At the numerical level, we derive the discretization form of Cahn-Hilliard and Allen-Cahn equations with the material point method (MPM) to effectively track the phase-field evolution, so as to avoid explicit handling of the boundary conditions at the interface. At the application level, we design a novel heuristic strategy to control specialized behaviors via user-defined schemes, including chemical potential, density curve, etc. We exhibit a set of numerous experimental results consisting of challenging scenarios in order to validate the effectiveness and versatility of the new unified approach. This flexible and highly stable framework, founded upon the unified treatment and seamless coupling among various phases, and effective numerical discretization, has its unique advantage in animation creation towards novel phenomena heavily involving phase transitions with artistic creativity and guidance.

Neural video game simulators emerged as powerful tools to generate and edit videos. Their idea is to represent games as the evolution of an environment’s state driven by the actions of its agents. While such a paradigm enables users to play a game action-by-action, its rigidity precludes more semantic forms of control. To overcome this limitation, we augment game models with prompts specified as a set of natural language actions and desired states. The result—a Promptable Game Model (PGM)—makes it possible for a user to play the game by prompting it with high- and low-level action sequences. Most captivatingly, our PGM unlocks the director’s mode, where the game is played by specifying goals for the agents in the form of a prompt. This requires learning “game AI”, encapsulated by our animation model, to navigate the scene using high-level constraints, play against an adversary, and devise a strategy to win a point. To render the resulting state, we use a compositional NeRF representation encapsulated in our synthesis model. To foster future research, we present newly collected, annotated and calibrated Tennis and Minecraft datasets. Our method significantly outperforms existing neural video game simulators in terms of rendering quality and unlocks applications beyond the capabilities of the current state of the art. Our framework, data, and models are available at snap-research.github.io/promptable-game-models.

This paper presents a new approach for 3D shape generation, inversion, and manipulation, through a direct generative modeling on a continuous implicit representation in wavelet domain. Specifically, we propose a compact wavelet representation with a pair of coarse and detail coefficient volumes to implicitly represent 3D shapes via truncated signed distance functions and multi-scale biorthogonal wavelets. Then, we design a pair of neural networks: a diffusion-based generator to produce diverse shapes in the form of the coarse coefficient volumes and a detail predictor to produce compatible detail coefficient volumes for introducing fine structures and details. Further, we may jointly train an encoder network to learn a latent space for inverting shapes, allowing us to enable a rich variety of whole-shape and region-aware shape manipulations. Both quantitative and qualitative experimental results manifest the compelling shape generation, inversion, and manipulation capabilities of our approach over the state-of-the-art methods.

3D scene synthesis facilitates and benefits many real-world applications. Most scene generators focus on making indoor scenes plausible via learning from training data and leveraging extra constraints such as adjacency and symmetry. Although the generated 3D scenes are mostly plausible with visually realistic layouts, they can be functionally unsuitable for human users to navigate and interact with furniture. Our key observation is that human activity plays a critical role and sufficient free space is essential for human-scene interactions. This is exactly where many existing synthesized scenes fail – the seemingly correct layouts are often not fit for living. To tackle this, we present a human-aware optimization framework Haisor for 3D indoor scene arrangement via reinforcement learning, which aims to find an action sequence to optimize the indoor scene layout automatically. Based on the hierarchical scene graph representation, an optimal action sequence is predicted and performed via Deep Q-Learning with Monte Carlo Tree Search (MCTS), where MCTS is our key feature to search for the optimal solution in long-term sequences and large action space. Multiple human-aware rewards are designed as our core criteria of human-scene interaction, aiming to identify the next smart action by leveraging powerful reinforcement learning. Our framework is optimized end-to-end by giving the indoor scenes with part-level furniture layout including part mobility information. Furthermore, our methodology is extensible and allows utilizing different reward designs to achieve personalized indoor scene synthesis. Extensive experiments demonstrate that our approach optimizes the layout of 3D indoor scenes in a human-aware manner, which is more realistic and plausible than original state-of-the-art generator results, and our approach produces superior smart actions, outperforming alternative baselines.