We introduce PhysMotion, a novel framework that leverages principled physics-based simulations to guide intermediate 3D representations generated from a single image and input conditions (e.g., applied force and torque), producing high-quality, physically plausible video generation. By utilizing continuum mechanics-based simulations as a prior knowledge, our approach addresses the limitations of traditional data-driven generative models and results in more consistent physically plausible motions. Our framework begins by reconstructing a feed-forward 3D Gaussian from a single image through geometry optimization. This representation is then time-stepped using Material Point Method (MPM) with continuum mechanics-based elastoplasticity models, which provides a strong foundation for realistic$d y$namics, albeit at a coarse level of detail. To enhance the geometry, appearance, and ensure spatiotemporal consistency, we refine the initial simulation using a text-to-image (T2I) diffusion model with cross-frame attention, resulting in a physically plausible video that retains intricate details comparable to the input image. We conduct comprehensive qualitative and quantitative evaluations to validate the efficacy of our method.

We present ElastoGen, a knowledge-driven AI model that generates physically accurate 4D elastodynamics. Unlike deep models that learn from video- or image-based observations, ElastoGen leverages the principles of physics and learns from established mathematical and optimization procedures. The core idea of ElastoGen is converting the differential equation, corresponding to the nonlinear force equilibrium, into a series of iterative local convolution-like operations, which naturally fit deep architectures. We carefully build our network module following this overarching design philosophy. ElastoGen is much more lightweight in terms of both training requirements and network scale than deep generative models. Because of its alignment with actual physical procedures, ElastoGen efficiently generates accurate dynamics for a wide range of hyperelastic materials and can be easily integrated with upstream and downstream deep modules to enable end-to-end 4D generation.

We introduce MPM Lite, a hybrid Lagrangian/Eulerian method that eliminates the need for particle-based quadrature at solve time. Standard Material Point Method (MPM) practices suffer from a performance bottleneck where expensive implicit solves are proportional to particle-per-cell (PPC) counts due to the the choices of particle-based quadrature and wide-stencil kernels. By contrast, MPM Lite treats particles primarily as carriers of kinematic state and material history. Conceptualizing the background Cartesian grid as a voxel hexahedral mesh, we resample particle states onto fixed-location quadrature points using efficient, compact linear kernels. This architectural shift allows force assembly and the entire time-integration process to proceed without accessing particles, thus making the solver's complexity independent of the particle count. At the core of our method is a novel stress transfer and stretch reconstruction strategy. To avoid non-physical averaging of deformation gradients, we resample the extensive Kirchhoff stress and derive a rotation-free deformation reference solution, which naturally supports an optimization-based incremental potential formulation. Consequently, MPM Lite can be implemented as modular resampling units coupled with an FEM-style integration module, enabling the direct use of off-the-shelf nonlinear solvers, preconditioners, and unambiguous boundary conditions. We demonstrate through extensive experiments that MPM Lite preserves the robustness and versatility of traditional MPM across diverse materials while delivering significant speedups in implicit settings while simultaneously improving explicit ones. Project page: https://mpmlite.github.io.

JGS2 is a Jacobi-like GPU simulation algorithm. It avoids the overshooting issue by augmenting each subproblem with a perturbation subspace that predicts the global influence of the local solve. The efficiency of JGS2 is due to Cubature-based subspace integration at each subproblem. Being a data-driven method, Cubature requires a set of representative deformed poses that cover deformations likely to occur in the simulation. This requirement is unlikely for high-resolution deformation with rich local details. Therefore, simulation performance and convergence degenerate when Cubature extrapolates. This paper proposes a training-free subspace integration algorithm based on classic Gaussian quadrature (GQ). We leverage the fact that the subproblem's subspace bases can be well-approximated by a low-degree multivariable polynomial, which suggests GQ an excellent candidate for Cubature substitute. To this end, we introduce a novel algorithm that adaptively generates the integration region for each subproblem. As a result, GQ integration can be analytically retrieved without cumbersome data generation and training. We also show how to handle frictional contact by modifying the pre-computed perturbation subspace. The resulting JGS2-GQ framework is more versatile than the vanilla JGS2 method. It is more stable for large and novel deformations, and is free of data generation and expensive training, while maintaining a near second-order convergence that is comparable to Newton. Performance-wise, JGS2-GQ is as efficient as JGS2, which is three orders faster than classic CPU methods and up to two orders faster than classic GPU algorithms. When novel deformation occurs, JGS2-GQ outperforms JGS2 over 50%.

Simulating heterogeneous multibody systems with both deformable and stiff components remains a challenge for GPU solvers. While Newton-Krylov methods are popular for their matrix-free nature and good GPU compatibility, they often suffer from severe ill-conditioning and slow convergence when handling stiff contacts and material disparities in deformable multibody systems. In this paper, we present Heterogeneous Subspace Corrections (HSC), a novel Newton-CG variant to efficiently simulate such complex systems. HSC decouples the system into two Krylov iterations: a Newton-CG procedure for deformable bodies and a Neumann-based iteration for the affine subsystem. We introduce a GPU-based Adaptive Cross Approximation (ACA) algorithm to exploit the low-rank nature of the coupling matrices, which manages to reduce the overhead of sparse matrix-vector multiplications substantially on the GPU. For the affine subsystem, we propose a dedicated data structure for fast assembling contact Hessians in parallel. A variety of experimental results demonstrate that our framework consistently outperforms existing GPU simulators, achieving convergence rates comparable to direct solvers even in scenes with high-resolution models and extensive stiff contacts.

Simulating large-scale articulated assemblies poses a significant challenge due to the numerical stiffness and geometric complexity of jointed structures. Conventional rigid body solvers struggle with the high nonlinearity induced by rotation parameterization. This difficulty becomes more pronounced for multiple two-way-coupled bodies. This paper introduces a novel framework that leverages the linear kinematic mapping of Affine Body Dynamics (ABD). As ABD targets near-rigid objects, the constitutive variations of different materials become negligible, which justifies a co-rotational approach to isolate geometric nonlinearities of the system. This insight enables the use of constant system matrices that can be pre-factorized throughout the simulation, even with fully implicit integration schemes. To manage the high DOF counts of large-scale systems, we map primal body coordinates onto a compact dual space defined by minimal joint degrees of freedom. By solving the resulting KKT systems, our method ensures exact constraint enforcement and physically accurate motion propagation. We provide a suite of specialized solvers tailored for diverse joint topologies, including chains, trees, closed loops, and irregular networks. Experimental results show that our approach achieves interactive rates for systems with hundreds of thousands of bodies on a single CPU core, while maintaining excellent stability at large time steps.

Capturing cloth motion with high fidelity is challenging due to fine-scale wrinkles, large deformation, and frequent self-occlusion. We present a 4D (spatio-temporal) cloth capture system that achieves 1 mm spatial resolution using only 16 RGB cameras. Our approach uses a two-level marker pattern: sparse, colored L-shaped markers provide robust detection and orientation, while dense noise patterns within each marker enable both marker identification and precise keypoint localization. By unwarping detected markers to a canonical frame, we factor out perspective distortion and most of cloth deformation, allowing the localizer to achieve sub-pixel accuracy. The localized keypoints are triangulated across views to form an incomplete point cloud. A physics-based optimization then deforms a template mesh to match the captured geometry while maintaining penetration-free constraints and physical plausibility for occluded regions. Our method produces temporally coherent sequences that faithfully capture fine wrinkles and folds even during complex motions with self-contact.

We present an efficient B-spline finite element method (FEM) for cloth simulation. While higher-order FEM has long promised higher accuracy, its adoption in cloth simulators has been limited by its larger computational costs while generating results with similar visual quality. Our contribution is a full algorithmic pipeline that makes cloth simulation using quadratic B-spline surfaces faster than standard linear FEM in practice while consistently improving accuracy and visual fidelity. Using quadratic B-spline basis functions, we obtain a globally C 1 -continuous displacement field that supports consistent discretization of both membrane and bending energies, effectively reducing locking artifacts and mesh dependence common to linear elements. To close the performance gap, we introduce a reduced integration scheme that separately optimizes quadrature rules for membrane and bending energies, an accelerated Hessian assembly procedure tailored to the spline structure, and an optimized linear solver based on partial factorization. Together, these optimizations make high-order, smooth cloth simulation competitive at scale, yielding an average 2× speedup over linear FEM in our tests. Extensive experiments demonstrate improved accuracy, wrinkle detail, and robustness, including contact-rich scenarios, relative to linear FEM and recent higher-order approaches. Our method enables realistic wrinkling dynamics across a wide range of material parameters and supports practical garment animation, providing a new promising spatial discretization for high-quality cloth simulation.

While yarn-level garments offer rich dynamic details and compelling visual realism compared to triangle-based models, their wide adoption is hindered by the immense computational cost due to the presence of a large number of degrees of freedom (DOFs). This paper proposes a novel simulation framework designed to enhance the performance and stability for numerical simulation of nonlinear, non-convex, and high-resolution knitwear. Our method generalizes the Douglas-Rachford Splitting (DRS) scheme to resolve the non-convex coupling between stretching, shearing, bending, twisting, and contacting at each yarn thread. A key contribution is a nested decomposition strategy that decouples the non-convex variational energy into independent and convex sub-problems. Such convexification improves solver robustness and removes the necessity for frequent line searches. We provide a theoretically grounded strategy for metric selection for each sub-problem, derived from an analysis of the convergence guarantee of DRS. Consequently, our method achieves close-to-optimal convergence along the nonlinear iterations rather than relying on ad-hoc parameter tuning. The paper also clarifies a formal connection between our generalized DRS and the ADMM (Alternating Direction Method of Multipliers) framework, extending the applicability of our analysis to a broader set of constrained dynamics problems. Experimental results demonstrate that our method robustly handles complex knitwear simulation scenes with superior efficiency, stability, and physical fidelity compared to existing methods. With a matrix-free GPU parallelization, our method allows an interactive simulation rate of knitwear of multi-million DOFs.

We introduce a novel approach to simulate the interaction between fluids and thin elastic solids without any penetration. Our approach is centered around an optimization system augmented with barriers, which aims to find a configuration that ensures the absence of penetration while enforcing incompressibility for the fluids and minimizing elastic potentials for the solids. Unlike previous methods that primarily focus on velocity coherence at the fluid-solid interfaces, we demonstrate the effectiveness and flexibility of explicitly resolving positional constraints, including both explicit representation of solid positions and the implicit representation of fluid level-set interface. To preserve the volume of the fluid, we propose a simple yet efficient approach that adjusts the associated level-set values. Additionally, we develop a distance metric capable of measuring the separation between an implicitly represented surface and a Lagrangian object of arbitrary codimension. By integrating the inertia, solid elastic potential, damping, barrier potential, and fluid incompressibility within a unified system, we are able to robustly simulate a wide range of processes involving fluid interactions with lower-dimensional objects such as shells and rods. These processes include topology changes, bouncing, splashing, sliding, rolling, floating, and more.

Traditional 3D garment creation is labor-intensive, involving sketching, modeling, UV mapping, and texturing, which are time-consuming and costly. Recent advances in diffusion-based generative models have enabled new possibilities for 3D garment generation from text prompts, images, and videos. However, existing methods either suffer from inconsistencies among multi-view images or require additional processes to separate cloth from the underlying human model. In this paper, we propose GarmentDreamer, a novel method that leverages 3D Gaussian Splatting (GS) as guidance to generate wearable, simulation-ready 3D garment meshes from text prompts. In contrast to using multi-view images directly predicted by generative models as guidance, our 3DGS guidance ensures consistent optimization in both garment deformation and texture synthesis. Our method introduces a novel garment augmentation module, guided by normal and RGBA information, and employs implicit Neural Texture Fields (NeTF) combined with Variational Score Distillation (VSD) to generate diverse geometric and texture details. We validate the effectiveness of our approach through comprehensive qualitative and quantitative experiments, showcasing the superior performance of GarmentDreamer over state-of-the-art alternatives11Demos and codes are available at https://xuan-li.github.io/GarmentDreamerDemo/.

Fourier Neural Operator (FNO) is a powerful and popular operator learning method. However, FNO is mainly used in forward prediction, yet a great many applications rely on solving inverse problems. In this paper, we propose an invertible Fourier Neural Operator (iFNO) for jointly tackling the forward and inverse problems. We developed a series of invertible Fourier blocks in the latent channel space to share the model parameters, exchange the information, and mutually regularize the learning for the bi-directional tasks. We integrated a variational auto-encoder to capture the intrinsic structures within the input space and to enable posterior inference so as to mitigate challenges of illposedness, data shortage, noises that are common in inverse problems. We proposed a three-step process to combine the invertible blocks and the VAE component for effective training. The evaluations on seven benchmark forward and inverse tasks have demonstrated the advantages of our approach. The code is available at \url{https://github.com/BayesianAIGroup/iFNO.}

Recent image-to-ЗD reconstruction models have greatly advanced geometry generation, but they still struggle to faithfully generate realistic appearance. To address this, we introduce ARM, a novel method that reconstructs high-quality 3D meshes and realistic appearance from sparse-view images. The core of ARM lies in decoupling geometry from appearance, processing appearance within the UV texture space. Unlike previous methods, ARM improves texture quality by explicitly back-projecting measurements onto the texture map and processing them in a UV space module with a global receptive field. To resolve ambiguities between material and illumination in input images, ARM introduces a material prior that encodes semantic appearance information, enhancing the robustness of appearance decomposition. Trained on just 8 H100 GPUs, ARM outperforms existing methods both quantitatively and qualitatively. Our project page is available at https://arm-aigc.github.io.

We demonstrate the feasibility of integrating physics-based animations of solids and fluids with 3D Gaussian Splatting (3DGS) to create novel effects in virtual scenes reconstructed using 3DGS. Leveraging the coherence of the Gaussian Splatting and Position-Based Dynamics (PBD) in the underlying representation, we manage rendering, view synthesis, and the dynamics of solids and fluids in a cohesive manner. Similar to GaussianShader, we enhance each Gaussian kernel with an added normal, aligning the kernel’s orientation with the surface normal to refine the PBD simulation. This approach effectively eliminates spiky noises that arise from rotational deformation in solids. It also allows us to integrate physically based rendering to augment the dynamic surface reflections on fluids. Consequently, our framework is capable of realistically reproducing surface highlights on dynamic fluids and facilitating interactions between scene objects and fluids from new views.

Recently single-view 3D generation via Gaussian splatting has emerged and developed quickly. They learn 3D Gaussians from 2D RGB images generated from pre-trained multi-view diffusion (MVD) models, and have shown a promising avenue for 3D generation through a single image. Despite the current progress, these methods still suffer from the inconsistency jointly caused by the geometric ambiguity in the 2D images, and the lack of structure of 3D Gaussians, leading to distorted and blurry 3D object generation. In this paper, we propose to fix these issues by GS-RGBN, a new RGBN-volume Gaussian Reconstruction Model designed to generate high-fidelity 3D objects from single-view images. Our key insight is a structured 3D representation can simultaneously mitigate the afore-mentioned two issues. To this end, we propose a novel hybrid Voxel-Gaussian representation, where a 3D voxel representation contains explicit 3D geometric information, eliminating the geometric ambiguity from 2D images. It also structures Gaussians during learning so that the optimization tends to find better local optima. Our 3D voxel representation is obtained by a fusion module that aligns RGB features and surface normal features, both of which can be estimated from 2D images. Extensive experiments demonstrate the superiority of our methods over prior works in terms of high-quality reconstruction results, robust generalization, and good efficiency.

This paper presents a novel pipeline named EnliveningGS, which enables active locomotion of 3D models represented with 3D Gaussian splatting (3DGS). We are inspired by the fact that real-world lives pose their bodies in a natural and physically meaningful manner by compressing or elongating muscle fibers embedded in the body. EnliveningGS aims to replicate the similar functionality of 3DGS models so that the object within a 3DGS scene acts like a living creature rather than a static shape —they walk, jump, and twist in the scene under provided motion trajectories driven by muscle activations. While the concept is straightforward, many challenging technical difficulties need to be taken care of. Synthesizing realistic locomotion of a 3DGS model embodies an inverse physics problem of very high dimensions. The core challenge is how to efficiently and robustly model frictional contacts between an "enlivened model" and the environment, as it is the composition of contact/collision/friction forces triggered by muscle activation that generates the final movement of the object. We propose a hybrid numerical method mixing LCP and penalty method to tackle this NP-hard problem robustly. Our pipeline also addresses the limitation of existing 3DGS deformation algorithms and inpainting the missing information when models move around.

Many works have succeeded in reconstructing Gaussian human avatars from multi-view videos. However, they either struggle to capture pose-dependent appearance details with a single MLP, or rely on a computationally intensive neural network to reconstruct high-fidelity appearance but with rendering performance degraded to non-real-time. We propose a novel Gaussian human avatar representation that can reconstruct high-fidelity pose-dependence appearance with details and meanwhile can be rendered in real time. Our Gaussian avatar is empowered by spatially distributed MLPs which are explicitly located on different positions on human body. The parameters stored in each Gaussian are obtained by interpolating from the outputs of its nearby MLPs based on their distances. To avoid undesired smooth Gaussian property changing during interpolation, for each Gaussian we define a set of Gaussian offset basis, and a linear combination of basis represents the Gaussian property offsets relative to the neutral properties. Then we propose to let the MLPs output a set of coefficients corresponding to the basis. In this way, although Gaussian coefficients are derived from interpolation and change smoothly, the Gaus-sian offset basis is learned freely without constraints. The smoothly varying coefficients combined with freely learned basis can still produce distinctly different Gaussian property offsets, allowing the ability to learn high-frequency spatial signals. We further use control points to constrain the Gaussians distributed on a surface layer rather than allowing them to be irregularly distributed inside the body, to help the human avatar generalize better when animated under novel poses. Compared to the state-of-the-art method, our method achieves better appearance quality with finer details while the rendering speed is significantly faster under novel views and novel poses.

Physics-based simulation is essential for developing and evaluating robot manipulation policies, particularly in scenarios involving deformable objects and complex contact interactions. However, existing simulators often struggle to balance computational efficiency with numerical accuracy, especially when modeling deformable materials with frictional contact constraints. We introduce an efficient subspace representation for the Incremental Potential Contact (IPC) method, leveraging model reduction to decrease the number of degrees of freedom. Our approach decouples simulation complexity from the resolution of the input model by representing elasticity in a low-resolution subspace while maintaining collision constraints on an embedded high-resolution surface. Our barrier formulation ensures intersection-free trajectories and configurations regardless of material stiffness, time step size, or contact severity. We validate our simulator through quantitative experiments with a soft bubble gripper grasping and qualitative demonstrations of placing a plate on a dish rack. The results demonstrate our simulator's efficiency, physical accuracy, computational stability, and robust handling of frictional contact, making it well-suited for generating demonstration data and evaluating downstream robot training applications. More details and supplementary material are on the website: https://sites.google.com/view/embedded-ipc.

Grasping is fundamental to robotic manipulation, and recent advances in large-scale grasping datasets have provided essential training data and evaluation benchmarks, accelerating the development of learning-based methods for robust object grasping. However, most existing datasets exclude deformable bodies due to the lack of scalable, robust simulation pipelines, limiting the development of generalizable models for compliant grippers and soft manipulands. To address these challenges, we present GRIP, a General Robotic Incremental Potential contact simulation dataset for universal grasping. GRIP leverages an optimized Incremental Potential Contact (IPC)-based simulator for multi-environment data generation, achieving up to 48× speedup while ensuring efficient, intersection- and inversion-free simulations for compliant grippers and deformable objects. Our fully automated pipeline generates and evaluates diverse grasp interactions across 1,200 objects and 100,000 grasp poses, incorporating both soft and rigid grippers. The GRIP dataset enables applications such as neural grasp generation and stress field prediction. We release GRIP to advance research in robotic manipulation, soft-gripper control, and physics-driven simulation at: https://bell0o.github.io/GRIP/.

With the rise of digital fashion, reusing high-quality garment assets to assemble new outfits has become increasingly important for improving design efficiency and reducing production costs. However, combining multiple garments often introduces complex inter-garment intersections that are difficult to resolve. In this paper, we propose a novel framework that introduces a midsurface representation to simplify multilayered garments for intersection-free outfit assembly. Each garment is approximated by a watertight tetrahedral enclosure, enabling efficient resolution of inter-garment collisions on the midsurface level. To assemble an outfit, our method progressively untangles pairs of single-layer midsurfaces and incrementally constructs a merged midsurface. To recover the intersection-free full geometry from these deformed midsurfaces and enable instantaneous transfer across different poses, we uses embedded anchors to drive inversion-free deformation of enclosing tetrahedral cages. Through various examples, we demonstrate that our method provides a scalable and automated solution for virtual outfit coordination, enabling the direct reuse of garment assets in high-fidelity, collision-free digital fashion workflows.

Abstract Persistent wrinkles are often observed on crumpled garments e.g., the wrinkles around the knees after sitting for a while. Such wrinkles can be easily recovered if not deformed for long, and otherwise be persistent. Since they are vital to the visual realism of cloth animation, we aim to simulate realistic looking persistent wrinkles. To this end, we present a physics‐inspired finegrained wrinkle model. Different from existing methods, we recognize the importance of the interplay between internal friction and plasticity during wrinkle formation. Furthermore, we model their time dependence for persistent wrinkles. Our model is capable of not only simulating realistic wrinkle patterns, but also their time‐dependent changes according to how long the deformation is maintained. Through extensive experiments, we show that our model is effective in simulating realistic spatial and temporal varying wrinkles, versatile in simulating different materials, and capable of generating more fine‐grained wrinkles than the state of the art.

Abstract Physics simulation is a cornerstone of many computer graphics applications, ranging from video games and virtual reality to visual effects and computational design. The number of techniques for physically‐based modeling and animation has thus skyrocketed over the past few decades, facilitating the simulation of a wide variety of materials and physical phenomena. This report captures the state‐of‐the‐art of multiphysics simulation for computer graphics applications. Although a lot of work has focused on simulating individual phenomena, here we put an emphasis on methods developed by the computer graphics community for simulating various physical phenomena and materials, as well as the interactions between them. These include combinations of discretization schemes, mathematical modeling frameworks, and coupling techniques. For the most commonly used methods we provide an overview of the state‐of‐the‐art and deliver valuable insights into the various approaches. A selection of software frameworks that offer out‐of‐the‐box multiphysics modeling capabilities is also presented. Finally, we touch on emerging trends in physics‐based animation that affect multiphysics simulation, including machine learning‐based methods which have become increasingly popular in recent years.

In vehicle trajectory prediction, traditional methods like Kalman filtering often rely heavily on user expertise and prior knowledge, while newer deep learning approaches, such as Long Short-Term Memory (LSTM) networks, also face challenges related to human intervention and subjective hyperparameter selection. This study proposes a systematic approach for Light Detection and Ranging (LiDAR)-based vehicle trajectory prediction, leveraging LSTM networks to predict vehicle trajectories and employing Bayesian optimization to automatically search for optimal hyperparameter values related to both the training scheme and LSTM architectures. In the experimental study, a custom vehicle trajectory dataset extracted from roadside LiDAR data, along with the V2X-Seq-TFD dataset, was utilized for network training and testing. The optimal LSTM network obtained through Bayesian optimization was compared against two benchmark models: a handcrafted LSTM network and a Kalman filter with a 2D constant velocity motion model. The results demonstrate that the proposed deep learning-based framework, with robust hyperparameter selection through Bayesian optimization, yields more accurate and consistent prediction performance than the benchmark models.

We present a novel contact model, termed Offset Geometric Contact (OGC), for guaranteed penetration-free simulation of codimensional objects with minimal computational overhead. Our method is based on constructing a volumetric shape by offsetting each face along its normal direction, ensuring orthogonal contact forces, thus allows large contact radius without artifacts. We compute vertex-specific displacement bounds to guarantee penetration-free simulation, which improves convergence and avoids the need for expensive continuous collision detection. Our method relies solely on massively parallel local operations, avoiding global synchronization and enabling efficient GPU implementation. Experiments demonstrate real-time, large-scale simulations with performance more than two orders of magnitude faster than prior methods while maintaining consistent computational budgets.

Online free-view navigation in volumetric videos requires high-quality rendering and real-time streaming in order to provide immersive user experiences. However, existing methods ( e.g. , dynamic NeRF and 3DGS) may not handle dynamic scenes with complex motions, and their models may not be streamable due to storage and bandwidth constraints. In this paper, we propose a novel 4D Gaussian Video (4DGV) approach that enables the creation and streaming of photorealistic, volumetric videos for dynamic scenes over the Internet. The core of our 4DGV is a novel streamable group of Gaussians (GOG) representation based on motion layering. Each GOG consists of static and dynamic points obtained via lifting 2D segmentation into 3D in motion layering, where the deformation of each dynamic point is represented as the temporal offset of its attributes. We also adaptively convert static points back to dynamic points to handle the appearance change, (e.g. , moving shadows and reflections), of static objects through optimization. To support real-time streaming of 4DGVs, we show that by applying quantization on Gaussian attributes and H.265 encoding on deformation offsets, our GOG representation can be significantly compressed (to around 6% of the original model size) without sacrificing the accuracy (PSNR loss less than 0.01dB). Extensive experiments on standard benchmarks demonstrate that our method outperforms state-of-the-art volumetric video approaches, with superior rendering quality and minimum storage overheads.

The knit structure consists of interlocked yarns, with each yarn comprising multiple plies comprising tens to hundreds of twisted fibers. This intricate geometry and the large number of geometric primitives present substantial challenges for achieving high-fidelity simulation and rendering in real-time applications. In this work, we introduce the first real-time framework that takes an animated stitch mesh as input and enhances it with yarn-level simulation and fiber-level rendering. Our approach relies on a knot-based representation to model interlocked yarn contacts. The knot positions are interpolated from the underlying mesh, and associated yarn control points are optimized using a physically inspired energy formulation, which is solved through a GPU-based Gauss-Newton scheme for real-time performance. The optimized control points are sent to the GPU rasterization pipeline and rendered as yarns with fiber-level details. In real-time rendering, we introduce several decomposition strategies to enable realistic lighting effects on complex knit structures, even under environmental lighting, while maintaining computational and memory efficiency. Our simulation faithfully reproduces yarn-level structures under deformations, e.g., stretching and shearing, capturing interlocked yarn behaviors. The rendering pipeline achieves near-ground-truth visual quality while being 120,000× faster than path tracing reference with fiber-level geometries. The whole system provides real-time performance and has been evaluated through various application scenarios, including knit simulation for small patches and full garments and yarn-level relaxation in the design pipeline.

In parallel simulation, convergence and parallelism are often seen as inherently conflicting objectives. Improved parallelism typically entails lighter local computation and weaker coupling, which unavoidably slow the global convergence. This paper presents a novel GPU algorithm that achieves convergence rates comparable to fullspace Newton's method while maintaining good parallelizability just like the Jacobi method. Our approach is built on a key insight into the phenomenon of overshoot. Overshoot occurs when a local solver aggressively minimizes its local energy without accounting for the global context, resulting in a local update that undermines global convergence. To address this, we derive a theoretically second-order optimal solution to mitigate overshoot. Furthermore, we adapt this solution into a pre-computable form. Leveraging Cubature sampling, our runtime cost is only marginally higher than the Jacobi method, yet our algorithm converges nearly quadratically as Newton's method. We also introduce a novel full-coordinate formulation for more efficient pre-computation. Our method integrates seamlessly with the incremental potential contact method and achieves second-order convergence for both stiff and soft materials. Experimental results demonstrate that our approach delivers high-quality simulations and outperforms state-of-the-art GPU methods with 50× to 100× better convergence.

Recent advances in large models have significantly advanced image-to-3D reconstruction. However, the generated models are often fused into a single piece, limiting their applicability in downstream tasks. This paper focuses on 3D garment generation, a key area for applications like virtual try-on with dynamic garment animations, which require garments to be separable and simulation-ready. We introduce Dress-1-to-3, a novel pipeline that reconstructs physics-plausible, simulation-ready separated garments with sewing patterns and humans from an in-the-wild image. Starting with the image, our approach combines a pre-trained image-to-sewing pattern generation model for creating coarse sewing patterns with a pre-trained multi-view diffusion model to produce multi-view images. The sewing pattern is further refined using a differentiable garment simulator based on the generated multi-view images. Versatile experiments demonstrate that our optimization approach substantially enhances the geometric alignment of the reconstructed 3D garments and humans with the input image. Furthermore, by integrating a texture generation module and a human motion generation module, we produce customized physics-plausible and realistic dynamic garment demonstrations. Our project page is https://dress-1-to-3.github.io/.

Whenever the concept of high-performance cloth simulation is brought up, GPU acceleration is almost always the first that comes to mind. Leveraging immense parallelization, GPU algorithms have demonstrated significant success recently, whereas CPU methods are somewhat overlooked. Indeed, the need for an efficient CPU simulator is evident and pressing. In many scenarios, high-end GPUs may be unavailable or are already allocated to other tasks, such as rendering and shading. A high-performance CPU alternative can greatly boost the overall system capability and user experience. Inspired by this demand, this paper proposes a CPU algorithm for high-resolution cloth simulation. By partitioning the garment model into multiple (but not massive) sub-meshes or domains, we assign per-domain computations to individual CPU processors. Borrowing the idea of projective dynamics that breaks the computation into global and local steps, our key contribution is a new parallelization paradigm at domains for both global and local steps so that domain-level calculations are sequential and lightweight. The CPU has much fewer processing units than a GPU. Our algorithm mitigates this disadvantage by wisely balancing the scale of the parallelization and convergence. We validate our method in a wide range of simulation problems involving high-resolution garment models. Performance-wise, our method is at least one order faster than existing CPU methods, and it delivers a similar performance compared with the state-of-the-art GPU algorithms in many examples, but without using a GPU.

In physics-based simulation of rigid or nearly rigid objects, collisions often become the primary performance bottleneck, particularly when enforcing intersection-free constraints. Previous simulation frameworks rely on primitive-level CCD algorithms. Due to the large number of colliding surface primitives to process, those methods are computationally intensive and heavily dependent on advanced parallel computing resources such as GPUs, which are often inaccessible due to competing tasks or capped threading capacity in applications like policy training for robotics. To address these limitations, we propose a sequential CCD algorithm for convex shapes undergoing constant affine motion. This approach uses the conservative advancement method to iteratively refine a lower-bound estimate of the TOI, exploiting the linearity of affine motion and the efficiency of convex shape distance computation. Our CCD algorithm integrates seamlessly into the ABD framework, achieving a 10-fold speed-up over primitive-level CCD. Its high single-threaded efficiency further enables significant throughput improvements via scene-level parallelism, making it well-suited for resource-constrained environments.

Hair cards remain a widely used representation for hair modeling in real-time applications, offering a practical trade-off between visual fidelity, memory usage, and performance. However, generating high-quality hair card models remains a challenging and labor-intensive task. This work presents an automated pipeline for converting strand-based hair models into hair card models with a limited number of cards and textures while preserving the hairstyle appearance. Our key idea is a novel differentiable representation where each strand is encoded as a projected 2D curve in the texture space, which enables end-to-end optimization with differentiable rendering while respecting the structures of the hair geometry. Based on this representation, we develop a novel algorithm pipeline, where we first cluster hair strands into initial hair cards and project the strands into the texture space. We then conduct a two-stage optimization, where our first stage optimizes the orientation of each hair card separately, and after strand projection, our second stage conducts joint optimization over the entire hair card model for fine-tuning. Our method is evaluated on a range of hairstyles, including straight, wavy, curly, and coily hair. To capture the appearance of short or coily hair, our method comes with support for hair caps and cross-card.

We present a lightweight system for reconstructing human geometry and appearance from sparse flashlight images. Our system produces detailed geometry including garment wrinkles and surface reflectance, which are exportable for direct rendering and relighting in traditional graphics pipelines. By capturing multi-view flashlight images using a consumer camera equipped with an co-located LED (e.g., a cell phone), we obtain view-specific shading cues that aid in the determination of surface orientation and help disambiguate between shading and material. To enable the reconstruction of geometry and appearance from sparse-view flashlight images, we integrate a pre-trained model into a differentiable physics-based rendering framework. As the learned image features from synthetic data cannot accurately reflect the shading features on real images, which is crucial for the high-quality reconstruction of geometry details and appearance, we propose to jointly optimize the image feature extractor with two MLPs for SDF and BRDF prediction using the differentiable physics-based rendering. Compared with existing methods for relightable human reconstruction, our system is able to produce high-fidelity 3D human models with more accurate geometry and appearance under the same condition. Our code and data are available at http://github.com/Jarvisss/Relightable_human_recon.

3D Gaussian Splatting (3DGS) models radiance fields as sparsely distributed 3D Gaussians, providing a compelling solution to novel view synthesis at high resolutions and real-time frame rates. However, deforming objects represented by 3D Gaussians remains a challenging task. Existing methods deform a 3DGS object by editing Gaussians geometrically. These approaches ignore the fact that it is the radiance field that rasterizes and renders the final image. The inconsistency between the deformed 3D Gaussians and the desired radiance field inevitably leads to artifacts in the final results. In this paper, we propose an interactive method for as-rigid-as-possible (ARAP) deformation of the Gaussian radiance fields. Specifically, after performing geometric edits on the Gaussians, we further optimize Gaussians to ensure its rasterization yields a similar result as the deformed radiance field. To facilitate this objective, we design radial features to mathematically describe the radial difference before and after the deformation, which are densely sampled across the radiance field. Additionally, we propose an adaptive anisotropic spatial low-pass filter to prevent aliasing issues during sampling and to preserve the field with the varying non-uniform sampling intervals. Users can interactively employ this tool to achieve large-scale ARAP deformations of the radiance field. Since our method maintains the consistency of the Gaussian radiance field before and after deformation, it avoids artifacts that are common in existing 3DGS deformation frameworks. Meanwhile, our method keeps the high quality and efficiency of 3DGS in rendering.

Creating relightable and animatable avatars from multi-view or monocular videos is a challenging task for digital human creation and virtual reality applications. Previous methods rely on neural radiance fields or ray tracing, resulting in slow training and rendering processes. By utilizing Gaussian Splatting, we propose a simple and efficient method to decouple body materials and lighting from sparse-view or monocular avatar videos, so that the avatar can be rendered simultaneously under novel viewpoints, poses, and lightings at interactive frame rates (6.9 fps). Specifically, we first obtain the canonical body mesh using a signed distance function and assign attributes to each mesh vertex. The Gaussians in the canonical space then interpolate from nearby body mesh vertices to obtain the attributes. We subsequently deform the Gaussians to the posed space using forward skinning, and combine the learnable environment light with the Gaussian attributes for shading computation. To achieve fast shadow modeling, we rasterize the posed body mesh from dense viewpoints to obtain the visibility. Our approach is not only simple but also fast enough to allow interactive rendering of avatar animation under environmental light changes. Experiments demonstrate that, compared to previous works, our method can render higher quality results at a faster speed on both synthetic and real datasets.

We show that physics-based simulations can be seamlessly integrated with NeRF to generate high-quality elastodynamics of real-world objects. Unlike existing methods, we discretize nonlinear hyperelasticity in a meshless way, obviating the necessity for intermediate auxiliary shape proxies like a tetrahedral mesh or voxel grid. A quadratic generalized moving least square is employed to capture nonlinear dynamics and large deformation on the implicit model. Such meshless integration enables versatile simulations of complex and codimensional shapes. We adaptively place the least-square kernels according to the NeRF density field to significantly reduce the complexity of the nonlinear simulation. As a result, physically realistic animations can be conveniently synthesized using our method for a wide range of hyperelastic materials at an interactive rate. For more information, please visit our project page.

We introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthe-sis. Employing a custom Material Point Method (MPM), our approach enriches 3D Gaussian kernels with physically meaningful kinematic deformation and mechanical stress attributes, all evolved in line with continuum mechanics principles. A defining characteristic of our method is the seamless integration between physical simulation and visual rendering: both components utilize the same 3D Gaussian kernels as their discrete representations. This negates the necessity for triangle/tetrahedron meshing, marching cubes, “cage meshes,” or any other geometry embedding, highlighting the principle of “what you see is what you simulate (WS2).” Our method demonstrates exceptional versatility across a wide variety of materials-including elastic entities, plastic metals, non-Newtonian fluids, and granular materials-showcasing its strong capabilities in creating diverse visual content with novel viewpoints and movements. Our project page is at: https://xpandora.github.io/PhysGaussian/

We present a framework for the interactive simulation of fluids coupled with rigid bodies that targets heterogeneous distributed computing architectures. Specifically, our proposed approach is well-suited for computer graphics applications that combine servers with large compute capactiy with low-end devices. In this setting, a global large-scale fluid simulation is performed on servers using high-end compute hardware, and local refinement of fluid and rigid body coupling is performed on a client with limited compute resources, such as a tablet or smartphone. We demonstrate the effectiveness of our framework to simulate large and complex scenes involving wind, ocean, and dynamic objects, all while providing plausible interactions through fluid-rigid coupling.

Existing diffusion-based text-to-3D generation methods primarily focus on producing visually realistic shapes and appearances, often neglecting the physical constraints necessary for downstream tasks. Generated models frequently fail to maintain balance when placed in physics-based simulations or 3D printed. This balance is crucial for satisfying user design intentions in interactive gaming, embodied AI, and robotics, where stable models are needed for reliable interaction. Additionally, stable models ensure that 3D-printed objects, such as figurines for home decoration, can stand on their own without requiring additional supports. To fill this gap, we introduce Atlas3D, an automatic and easy-to-implement method that enhances existing Score Distillation Sampling (SDS)-based text-to-3D tools. Atlas3D ensures the generation of self-supporting 3D models that adhere to physical laws of stability under gravity, contact, and friction. Our approach combines a novel differentiable simulation-based loss function with physically inspired regularization, serving as either a refinement or a post-processing module for existing frameworks. We verify Atlas3D's efficacy through extensive generation tasks and validate the resulting 3D models in both simulated and real-world environments.

PBD and its extension, XPBD, have been predominantly applied to compliant constrained elastodynamics, with their potential in finite strain (visco-) elastoplasticity remaining underexplored. XPBD is often perceived to stand in contrast to other meshless methods, such as the MPM. MPM is based on discretizing the weak form of governing partial differential equations within a continuum domain, coupled with a hybrid Lagrangian-Eulerian method for tracking deformation gradients. In contrast, XPBD formulates specific constraints, whether hard or compliant, to positional degrees of freedom. We revisit this perception by investigating the potential of XPBD in handling inelastic materials that are described with classical continuum mechanics-based yield surfaces and elastoplastic flow rules. Our inspiration is that a robust estimation of the velocity gradient is a sufficiently useful key to effectively tracking deformation gradients in XPBD simulations. By further incorporating implicit inelastic constitutive relationships, we introduce a plasticity in-the-loop updated Lagrangian augmentation to XPBD. This enhancement enables the simulation of elastoplastic, viscoplastic, and granular substances following their standard constitutive laws. We demonstrate the effectiveness of our method through high-resolution and real-time simulations of diverse materials such as snow, sand, and plasticine, and its integration with standard XPBD simulations of cloth and water.

Since the past decade, Light Detection and Ranging (LiDAR) data have been extensively adopted for traffic object recognition tasks. Existing methodologies often assume LiDAR data are acquired under normal weather conditions. Nevertheless, many researchers have observed that the LiDAR data captured under inclement weather are often contaminated with noises such as fog and snow, which may deteriorate the data quality and lead to false detections in traffic object recognition. This paper proposes a neighborhood-based noise removal methodology to eliminate snow noises from LiDAR data. It identifies a point of interest from a specific laser channel as an outlier, if the number of neighboring points in the same channel within a dynamic search radius is fewer than a threshold. Unlike existing methods that filter the entire LiDAR point cloud, the proposed methodology processes LiDAR data channel-by-channel, which helps reduce the data dimensionality and decouple the snow effects along the vertical axis of the 3D point cloud, leading to more effective and efficient outlier detection. Furthermore, by dynamically changing the search radius based on the point-to-sensor distance rather than adopting a fixed search radius, the proposed methodology can account for the reduced point density at far distances caused by the non-uniformity of LiDAR data. In the experimental study, the proposed methodology is compared against some existing LiDAR de-noising approaches, including two state-of-the-art methods, and demonstrates superior performance in both accuracy (i.e., F1 score$=$98.3%) and efficiency.

Knowledge distillation (KD) has become a widely used technique for model compression and knowledge transfer. We find that the standard KD method performs the knowledge alignment on an individual sample indirectly via class prototypes and neglects the structural knowledge between different samples, namely, knowledge correlation. Although recent contrastive learning-based distillation methods can be decomposed into knowledge alignment and correlation, their correlation objectives undesirably push apart representations of samples from the same class, leading to inferior distillation results. To improve the distillation performance, in this work, we propose a novel knowledge correlation objective and introduce the dual-level knowledge distillation (DLKD), which explicitly combines knowledge alignment and correlation together instead of using one single contrastive objective. We show that both knowledge alignment and correlation are necessary to improve the distillation performance. In particular, knowledge correlation can serve as an effective regularization to learn generalized representations. The proposed DLKD is task-agnostic and model-agnostic, and enables effective knowledge transfer from supervised or self-supervised pretrained teachers to students. Experiments show that DLKD outperforms other state-of-the-art methods on a large number of experimental settings including: 1) pretraining strategies; 2) network architectures; 3) datasets; and 4) tasks.

We introduce vertex block descent, a block coordinate descent solution for the variational form of implicit Euler through vertex-level Gauss-Seidel iterations. It operates with local vertex position updates that achieve reductions in global variational energy with maximized parallelism. This forms a physics solver that can achieve numerical convergence with unconditional stability and exceptional computation performance. It can also fit in a given computation budget by simply limiting the iteration count while maintaining its stability and superior convergence rate. We present and evaluate our method in the context of elastic body dynamics, providing details of all essential components and showing that it outperforms alternative techniques. In addition, we discuss and show examples of how our method can be used for other simulation systems, including particle-based simulations and rigid bodies.

We propose a GPU-based iterative method for accelerated elastodynamic simulation with the log-barrier-based contact model. While Newton's method is a conventional choice for solving the interior-point system, the presence of ill-conditioned log barriers often necessitates a direct solution at each linearized substep and costs substantial storage and computational overhead. Moreover, constraint sets that vary in each iteration present additional challenges in algorithm convergence. Our method employs a novel barrier-augmented Lagrangian method to improve system conditioning and solver efficiency by adaptively updating an augmentation constraint sets. This enables the utilization of a scalable, inexact Newton-PCG solver with sparse GPU storage, eliminating the need for direct factorization. We further enhance PCG convergence speed with a domain-decomposed warm start strategy based on an eigenvalue spectrum approximated through our in-time assembly. Demonstrating significant scalability improvements, our method makes simulations previously impractical on 128 GB of CPU memory feasible with only 8 GB of GPU memory and orders-of-magnitude faster. Additionally, our method adeptly handles stiff problems, surpassing the capabilities of existing GPU-based interior-point methods. Our results, validated across various complex collision scenarios involving intricate geometries and large deformations, highlight the exceptional performance of our approach.

This paper pushes the performance of cloth simulation, making the simulation interactive even for high-resolution garment models while keeping every triangle untangled. The penetration-free guarantee is inspired by the interior point method, which converts the inequality constraints to barrier potentials. We propose a major overhaul of this modality within the projective dynamics framework by leveraging an adaptive weighting mechanism inspired by barrier formulation. This approach does not depend on the distance between mesh primitives, but on the virtual life span of a collision event and thus keeps all the vertices within feasible region. Such a non-distance barrier model allows a new way to integrate collision resolution into the simulation pipeline. Another contributor to the performance boost comes from the subspace reuse strategy. This is based on the observation that low-frequency strain propagation is near orthogonal to the deformation induced by collisions or self-collisions, often of high frequency. Subspace reuse then takes care of low-frequency residuals, while high-frequency residuals can also be effectively smoothed by GPU-based iterative solvers. We show that our method outperforms existing fast cloth simulators by at least one order while producing high-quality animations of high-resolution models.

The rapid advancement of digital fashion and generative AI technology calls for an automated approach to transform digital sewing patterns into well-fitted garments on human avatars. When given a sewing pattern with its associated sewing relationships, the primary challenge is to establish an initial arrangement of sewing pieces that is free from folding and intersections. This setup enables a physics-based simulator to seamlessly stitch them into a digital garment, avoiding undesirable local minima. To achieve this, we harness AI classification, heuristics, and numerical optimization. This has led to the development of an innovative hybrid system that minimizes the need for user intervention in the initialization of garment pieces. The seeding process of our system involves the training of a classification network for selecting seed pieces, followed by solving an optimization problem to determine their positions and shapes. Subsequently, an iterative selection-arrangement procedure automates the selection of pattern pieces and employs a phased initialization approach to mitigate local minima associated with numerical optimization. Our experiments confirm the reliability, efficiency, and scalability of our system when handling intricate garments with multiple layers and numerous pieces. According to our findings, 68 percent of garments can be initialized with zero user intervention, while the remaining garments can be easily corrected through user operations.

We present X-SLAM, a real-time dense differentiable SLAM system that leverages the complex-step finite difference (CSFD) method for efficient calculation of numerical derivatives, bypassing the need for a large-scale computational graph. The key to our approach is treating the SLAM process as a differentiable function, enabling the calculation of the derivatives of important SLAM parameters through Taylor series expansion within the complex domain. Our system allows for the real-time calculation of not just the gradient, but also higher-order differentiation. This facilitates the use of high-order optimizers to achieve better accuracy and faster convergence. Building on X-SLAM, we implemented end-to-end optimization frameworks for two important tasks: camera relocalization in wide outdoor scenes and active robotic scanning in complex indoor environments. Comprehensive evaluations on public benchmarks and intricate real scenes underscore the improvements in the accuracy of camera relocalization and the efficiency of robotic navigation achieved through our task-aware optimization. The code and data are available at https://gapszju.github.io/X-SLAM.

This paper presents volumetric homogenization, a spatially varying homogenization scheme for knitwear simulation. We are motivated by the observation that macro-scale fabric dynamics is strongly correlated with its underlying knitting patterns. Therefore, homogenization towards a single material is less effective when the knitting is complex and non-repetitive. Our method tackles this challenge by homogenizing the yarn-level material locally at volumetric elements. Assigning a virtual volume of a knitting structure enables us to model bending and twisting effects via a simple volume-preserving penalty and thus effectively alleviates the material nonlinearity. We employ an adjoint Gauss-Newton formulation[Zehnder et al. 2021] to battle the dimensionality challenge of such per-element material optimization. This intuitive material model makes the forward simulation GPU-friendly. To this end, our pipeline also equips a novel domain-decomposed subspace solver crafted for GPU projective dynamics, which makes our simulator hundreds of times faster than the yarn-level simulator. Experiments validate the capability and effectiveness of volumetric homogenization. Our method produces realistic animations of knitwear matching the quality of full-scale yarn-level simulations. It is also orders of magnitude faster than existing homogenization techniques in both the training and simulation stages.

We introduce a variational formulation for simulating sticky interactions between elastoplastic solids. Our method brings a wider range of material behaviors into the reach of the Incremental Potential Contact (IPC) solver recently developed by (Li et al. 2020). Extending IPC requires several contributions. We first augment IPC with the classical Raous-Cangemi-Cocou (RCC) adhesion model. This allows us to robustly simulate the sticky interactions between arbitrary codimensional-0, 1, and 2 geometries. To enable user-friendly practical adoptions of our method, we further introduce a physically parametrized, easily controllable normal adhesion formulation based on the unsigned distance, which is fully compatible with IPC's barrier formulation. Furthermore, we propose a smoothly clamped tangential adhesion model that naturally models intricate behaviors including debonding. Lastly, we perform benchmark studies comparing our method with the classical models as well as real-world experimental results to demonstrate the efficacy of our method.

We propose an efficient cloth simulation method that combines the merits of two drastically different numerical procedures, namely the subspace integration and parallelizable iterative relaxation. We show those two methods can be organically coupled within the framework of projective dynamics (PD), where both low- and high-frequency cloth motions are effectively and efficiently computed. Our method works seamlessly with the state-of-the-art contact handling algorithm, the incremental potential contact (IPC), to offer the non-penetration guarantee of the resulting animation. Our core ingredient centers around the utilization of subspace for the expedited convergence of Jacobi-PD. This involves solving the reduced global system and smartly employing its precomputed factorization. In addition, we incorporate a time-splitting strategy to handle the frictional self-contacts.

Unsupervised image translation (UIT) studies the mapping between two image domains. Since such mappings are under-constrained, existing research has pursued various desirable properties such as distributional matching or two-way consistency. In this paper, we re-examine UIT from a new perspective: distributional semantics consistency, based on the observation that data variations contain semantics, e.g., shoes varying in colors. Further, the semantics can be multi-dimensional, e.g., shoes also varying in style, functionality, etc. Given two image domains, matching these semantic dimensions during UIT will produce mappings with explicable correspondences, which has not been investigated previously. We propose distributional semantics mapping (DSM), the first UIT method which explicitly matches semantics between two domains. We show that distributional semantics has been rarely considered within and beyond UIT, even though it is a common problem in deep learning. We evaluate DSM on several benchmark datasets, demonstrating its general ability to capture distributional semantics. Extensive comparisons show that DSM not only produces explicable mappings, but also improves image quality in general.

In this paper, we present a GPU algorithm for finite element hyperelastic simulation. We show that the interior-point method, known to be effective for robust collision resolution, can be coupled with non-Newton procedures and be massively sped up on the GPU. Newton's method has been widely chosen for the interior-point family, which fully solves a linear system at each step. After that, the active set associated with collision/contact constraints is updated. Mimicking this routine using a non-Newton optimization (like gradient descent or ADMM) unfortunately does not deliver expected accelerations. This is because the barrier functions employed in an interior-point method need to be updated at every iteration to strictly confine the search to the feasible region. The associated cost (e.g., per-iteration CCD) quickly overweights the benefit brought by the GPU, and a new parallelism modality is needed. Our algorithm is inspired by the domain decomposition method and designed to move interior-point-related computations to local domains as much as possible. We minimize the size of each domain (i.e., a stencil) by restricting it to a single element, so as to fully exploit the capacity of modern GPUs. The stencil-level results are integrated into a global update using a novel hybrid sweep scheme. Our algorithm is locally second-order offering better convergence. It enables simulation acceleration of up to two orders over its CPU counterpart. We demonstrate the scalability, robustness, efficiency, and quality of our algorithm in a variety of simulation scenarios with complex and detailed collision geometries.

In this article, we present a four-layer distributed simulation system and its adaptation to the Material Point Method (MPM). The system is built upon a performance portable C++ programming model targeting major High-Performance-Computing (HPC) platforms. A key ingredient of our system is a hierarchical block-tile-cell sparse grid data structure that is distributable to an arbitrary number of Message Passing Interface (MPI) ranks. We additionally propose strategies for efficient dynamic load balance optimization to maximize the efficiency of MPI tasks. Our simulation pipeline can easily switch among backend programming models, including OpenMP and CUDA, and can be effortlessly dispatched onto supercomputers and the cloud. Finally, we construct benchmark experiments and ablation studies on supercomputers and consumer workstations in a local network to evaluate the scalability and load balancing criteria. We demonstrate massively parallel, highly scalable, and gigascale resolution MPM simulations of up to 1.01 billion particles for less than 323.25 seconds per frame with 8 OpenSSH-connected workstations.

We present a novel hybrid Lagrangian/Eulerian method for simulating inelastic flows that generates high-quality particle distributions with adaptive volumes. At its core, our approach integrates an updated Lagrangian time discretization of continuum mechanics with the Power Particle-In-Cell geometric representation of deformable materials. As a result, we obtain material points described by optimized density kernels that precisely track the varying particle volumes both spatially and temporally. For efficient CFL-rate simulations, we also propose an implicit time integration for our system using a non-linear Gauss-Seidel solver inspired by X-PBD, viewing Eulerian nodal velocities as primal variables. We demonstrate the versatility of our method with simulations of mesoscale bubbles, sands, liquid, and foams.

In this paper, we address two limitations of dihedral angle based discrete bending (DAB) models, i.e. the indefiniteness of their energy Hessian and their vulnerability to geometry degeneracies. To tackle the indefiniteness issue, we present novel analytic expressions for the eigensystem of a DAB energy Hessian. Our expressions reveal that DAB models typically have positive, negative, and zero eigenvalues, with four of each, respectively. By using these expressions, we can efficiently project an indefinite DAB energy Hessian as positive semi-definite analytically. To enhance the stability of DAB models at degenerate geometries, we propose rectifying their indefinite geometric stiffness matrix by using orthotropic geometric stiffness matrices with adaptive parameters calculated from our analytic eigensystem. Among the twelve motion modes of a dihedral element, our resulting Hessian for DAB models retains only the desirable bending modes, compared to the undesirable altitude-changing modes of the exact Hessian with original geometric stiffness, all modes of the Gauss-Newton approximation without geometric stiffness, and no modes of the projected Hessians with inappropriate geometric stiffness. Additionally, we suggest adjusting the compression stiffness according to the Kirchhoff-Love thin plate theory to avoid over-compression. Our method not only ensures the positive semidefiniteness but also avoids instability caused by large bending forces at degenerate geometries. To demonstrate the benefit of our approaches, we show comparisons against existing methods on the simulation of cloth and thin plates in challenging examples.

We present a robust and efficient method for simulating Lagrangian solid-fluid coupling based on a new operator splitting strategy. We use variational formulations to approximate fluid properties and solid-fluid interactions, and introduce a unified two-way coupling formulation for SPH fluids and FEM solids using interior point barrier-based frictional contact. We split the resulting optimization problem into a fluid phase and a solid-coupling phase using a novel time-splitting approach with augmented contact proxies , and propose efficient custom linear solvers. Our technique accounts for fluids interaction with nonlinear hyperelastic objects of different geometries and codimensions, while maintaining an algorithmically guaranteed non-penetrating criterion. Comprehensive benchmarks and experiments demonstrate the efficacy of our method.

Generating new images with desired properties (e.g. new view/poses) from source images has been enthusiastically pursued recently, due to its wide range of potential applications. One way to ensure high-quality generation is to use multiple sources with complementary information such as different views of the same object. However, as source images are often misaligned due to the large disparities among the camera settings, strong assumptions have been made in the past with respect to the camera(s) or/and the object in interest, limiting the application of such techniques. Therefore, we propose a new general approach which models multiple types of variations among sources, such as view angles, poses, facial expressions, in a unified framework, so that it can be employed on datasets of vastly different nature. We verify our approach on a variety of data including humans bodies, faces, city scenes and 3D objects. Both the qualitative and quantitative results demonstrate the better performance of our method than the state of the art.

We introduce a deep architecture named HoD-Net to enable high-order differentiability for deep learning. HoD-Net is based on and generalizes the complex-step finite difference (CSFD) method. While similar to classic finite difference, CSFD approaches the derivative of a function from a higher-dimension complex domain, leading to highly accurate and robust differentiation computation without numerical stability issues. This method can be coupled with backpropagation and adjoint perturbation methods for an efficient calculation of high-order derivatives. We show how this numerical scheme can be leveraged in challenging deep learning problems, such as high-order network training, deep learning-based physics simulation, and neural differential equations.

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced in commonly used cross-entropy loss. Based on the predicted boundaries detected from the segmentation results using current network parameters, we formulate the boundary alignment problem as a differentiable direction vector prediction problem to guide the movement of predicted boundaries in each iteration. Our loss is model-agnostic and can be plugged in to the training of segmentation networks to improve the boundary details. Experimental results show that training with the active boundary loss can effectively improve the boundary F-score and mean Intersection-over-Union on challenging image and video object segmentation datasets.

To overcome the high dimensionality problem of data, learning feature representations for clustering has been widely studied. In this work, we propose Disentangling Latent Space Clustering (DLS-Clustering), a new clustering framework that directly learns cluster assignments from disentangled latent spacing without additional clustering methods. We enforce the encoder and the generator of GAN to form an encoder-generator pair in addition to the generator-encoder pair. We train the encoder-generator pair using real data, which can implicitly estimate the real conditional distribution. Meanwhile, this framework enforces the outputs of the encoder to match the inputs of GAN and the prior noise distribution, which disentangles latent space into two parts: one-hot discrete and continuous latent variables. The former can be directly expressed as clusters and the latter represents remaining unspecified factors. Our experiments show that the proposed method achieves the optimal disentanglement performance and outperforms existing generative model-based clustering methods.

In this paper, we propose a neural network-based approach for learning to represent the behavior of plastic solid materials ranging from rubber and metal to sand and snow. Unlike elastic forces such as spring forces, these plastic forces do not result from the positional gradient of any potential energy, imposing great challenges on the stability and flexibility of their simulation. Our method effectively resolves this issue by learning a generalizable plastic energy whose derivative closely matches the analytical behavior of plastic forces. Our method, for the first time, enables the simulation of a wide range of arbitrary elasticity-plasticity combinations using time step-independent, unconditionally stable optimization-based time integrators. We demonstrate the efficacy of our method by learning and producing challenging 2D and 3D effects of metal, sand, and snow with complex dynamics.

We consider semantic image segmentation. Our method is inspired by Bayesian deep learning which improves image segmentation accuracy by modeling the uncertainty of the network output. In contrast to uncertainty, our method directly learns to predict the erroneous pixels of a segmentation network, which is modeled as a binary classification problem. It can speed up training comparing to the Monte Carlo integration often used in Bayesian deep learning. It also allows us to train a branch to correct the labels of erroneous pixels. Our method consists of three stages: (i) predict pixel-wise error probability of the initial result, (ii) redetermine new labels for pixels with high error probability, and (iii) fuse the initial result and the redetermined result with respect to the error probability. We formulate the error-pixel prediction problem as a classification task and employ an error-prediction branch in the network to predict pixel-wise error probabilities. We also introduce a detail branch to focus the training process on the erroneous pixels. We have experimentally validated our method on the Cityscapes and ADE20K datasets. Our model can be easily added to various advanced segmentation networks to improve their performance. Taking DeepLabv3+ as an example, our network can achieve 82.88% of mIoU on Cityscapes testing dataset and 45.73% on ADE20K validation dataset, improving corresponding DeepLabv3+ results by 0.74% and 0.13% respectively.

Recent technological advancements in computer vision algorithms and data acquisition devices have greatly facilitated the research and applications of deep learning-based traffic object recognition from Light Detection and Ranging (LiDAR) data. The majority of existing methodologies applied deep learning (DL)-based techniques, especially Convolutional Neural Networks (CNNs), for vehicle detection and tracking on autonomous driving datasets. Nevertheless, fewer studies were focused on DL-based vehicle detection using roadside LiDAR data, partially due to the lack of publicly available roadside LiDAR datasets for network training and testing. This paper develops a novel framework based on CNNs and LiDAR data for automated vehicle detection. It leverages the domain knowledge of CNNs trained on large-scale autonomous driving datasets for vehicle detection from roadside LiDAR data. In the experimental study, roadside LiDAR data were collected at a road intersection in Reno, Nevada, U.S. Meanwhile, a CNN architecture was proposed to detect vehicles from LiDAR data through 3D bounding boxes. The proposed CNN was modified from the established PointPillars network by adding dense connections to the convolutional layers to achieve more comprehensive feature extraction. Three CNNs, including the proposed CNN, PointPillars, and YOLOv4, were trained and tested on PandaSet, a publicly available large-scale autonomous driving LiDAR dataset. Subsequently, the trained CNNs were reused for vehicle detection from the captured roadside LiDAR data. The experimental results demonstrated that the proposed CNN outperformed the others in the testing metrics. All three networks showed good performance on vehicle detection from the captured roadside LiDAR data.

This study presents a new method for modeling the interaction between compressible flow, shock waves, and deformable structures, emphasizing destructive dynamics. Extending advances in time-splitting compressible flow and the Material Point Methods (MPM), we develop a hybrid Eulerian and Lagrangian/Eulerian scheme for monolithic flow-structure interactions. We adopt the second-order WENO scheme to advance the continuity equation. To stably resolve deforming boundaries with sub-cell particles, we propose a blending treatment of reflective and passable boundary conditions inspired by the theory of porous media. The strongly coupled velocity-pressure system is discretized with a new mixed-order finite element formulation employing B-spline shape functions. Shock wave propagation, temperature/density-induced buoyancy effects, and topology changes in solids are unitedly captured.

We present a simulation framework for multibody dynamics via a universal variational integration. Our method naturally supports mixed rigid-deformables and mixed codimensional geometries, while providing guaranteed numerical convergence and accurate resolution of contact, friction, and a wide range of articulation constraints. We unify (1) the treatment of simulation degrees of freedom for rigid and soft bodies by formulating them both in terms of Lagrangian nodal displacements, (2) the handling of general linear equality joint constraints through an efficient change-of-variable strategy, (3) the enforcement of nonlinear articulation constraints based on novel distance potential energies, (4) the resolution of frictional contact between mixed dimensions and bodies with a variational Incremental Potential Contact formulation, and (5) the modeling of generalized restitution through semi-implicit Rayleigh damping. We conduct extensive unit tests and benchmark studies to demonstrate the efficacy of our method.

Simulating stiff materials in applications where deformations are either not significant or else can safely be ignored is a fundamental task across fields. Rigid body modeling has thus long remained a critical tool and is, by far, the most popular simulation strategy currently employed for modeling stiff solids. At the same time, rigid body methods continue to pose a number of well known challenges and trade-offs including intersections, instabilities, inaccuracies, and/or slow performances that grow with contact-problem complexity. In this paper we revisit the stiff body problem and present ABD, a simple and highly effective affine body dynamics framework, which significantly improves state-of-the-art for simulating stiff-body dynamics. We trace the challenges in rigid-body methods to the necessity of linearizing piecewise-rigid trajectories and subsequent constraints. ABD instead relaxes the unnecessary (and unrealistic) constraint that each body's motion be exactly rigid with a stiff orthogonality potential, while preserving the rigid body model's key feature of a small coordinate representation. In doing so ABD replaces piecewise linearization with piecewise linear trajectories. This, in turn, combines the best of both worlds: compact coordinates ensure small, sparse system solves, while piecewise-linear trajectories enable efficient and accurate constraint (contact and joint) evaluations. Beginning with this simple foundation, ABD preserves all guarantees of the underlying IPC model we build it upon, e.g., solution convergence, guaranteed non-intersection, and accurate frictional contact. Over a wide range and scale of simulation problems we demonstrate that ABD brings orders of magnitude performance gains (two- to three-orders on the CPU and an order more when utilizing the GPU, obtaining 10, 000× speedups) over prior IPC-based methods, while maintaining simulation quality and nonintersection of trajectories. At the same time ABD has comparable or faster timings when compared to state-of-the-art rigid body libraries optimized for performance without guarantees, and successfully and efficiently solves challenging simulation problems where both classes of prior rigid body simulation methods fail altogether.

We present a GPU algorithm for deformable simulation. Our method offers good computational efficiency and penetration-free guarantee at the same time, which are not common with existing techniques. The main idea is an algorithmic integration of projective dynamics (PD) and incremental potential contact (IPC). PD is a position-based simulation framework, favored for its robust convergence and convenient implementation. We show that PD can be employed to handle the variational optimization with the interior point method e.g., IPC. While conceptually straightforward, this requires a dedicated rework over the collision resolution and the iteration modality to avoid incorrect collision projection with improved numerical convergence. IPC exploits a barrier-based formulation, which yields an infinitely large penalty when the constraint is on the verge of being violated. This mechanism guarantees intersection-free trajectories of deformable bodies during the simulation, as long as they are apart at the rest configuration. On the downside, IPC brings a large amount of nonlinearity to the system, making PD slower to converge. To mitigate this issue, we propose a novel GPU algorithm named A-Jacobi for faster linear solve at the global step of PD. A-Jacobi is based on Jacobi iteration, but it better harvests the computation capacity on modern GPUs by lumping several Jacobi steps into a single iteration. In addition, we also re-design the CCD root finding procedure by using a new minimum-gradient Newton algorithm. Those saved time budgets allow more iterations to accommodate stiff IPC barriers so that the result is both realistic and collision-free. Putting together, our algorithm simulates complicated models of both solids and shells on the GPU at an interactive rate or even in real time.

Quantization has proven effective in high-resolution and large-scale simulations, which benefit from bit-level memory saving. However, identifying a quantization scheme that meets the requirement of both precision and memory efficiency requires trial and error. In this paper, we propose a novel framework to allow users to obtain a quantization scheme by simply specifying either an error bound or a memory compression rate. Based on the error propagation theory, our method takes advantage of auto-diff to estimate the contributions of each quantization operation to the total error. We formulate the task as a constrained optimization problem, which can be efficiently solved with analytical formulas derived for the linearized objective function. Our workflow extends the Taichi compiler and introduces dithering to improve the precision of quantized simulations. We demonstrate the generality and efficiency of our method via several challenging examples of physics-based simulation, which achieves up to 2.5× memory compression without noticeable degradation of visual quality in the results. Our code and data are available at https://github.com/Hanke98/AutoQantizer.

In this paper, we propose an effective global relation learning algorithm to recommend an appropriate location of a building unit for in-game customization of residential home complex. Given a construction layout, we propose a visual context-aware graph generation network that learns the implicit global relations among the scene components and infers the location of a new building unit. The proposed network takes as input the scene graph and the corresponding top-view depth image. It provides the location recommendations for a newly added building units by learning an auto-regressive edge distribution conditioned on existing scenes. We also introduce a global graph-image matching loss to enhance the awareness of essential geometry semantics of the site. Qualitative and quantitative experiments demonstrate that the recommended location well reflects the implicit spatial rules of components in the residential estates, and it is instructive and practical to locate the building units in the 3D scene of the complex construction.

This paper proposes a novel location-aware deep-learning-based single image reflection removal method. Our network has a reflection detection module to regress a probabilistic reflection confidence map, taking multi-scale Laplacian features as inputs. This probabilistic map tells if a region is reflection-dominated or transmission-dominated, and it is used as a cue for the network to control the feature flow when predicting the reflection and transmission layers. We design our network as a recurrent network to progressively refine reflection removal results at each iteration. The novelty is that we leverage Laplacian kernel parameters to emphasize the boundaries of strong reflections. It is beneficial to strong reflection detection and substantially improves the quality of reflection removal results. Extensive experiments verify the superior performance of the proposed method over state-of-the-art approaches. Our code and the pre-trained model can be found at https://github.com/zdlarr/Location-aware-SIRR.

Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision. Generative Adversarial Networks (GANs) as an implicit approach have achieved great successes in this direction and therefore been employed widely. However, GANs are known to suffer from issues such as mode collapse, non-structured latent space, being unable to compute likelihoods, etc. In this paper, we propose a new unsupervised non-parametric method named mixture of infinite conditional GANs or MIC-GANs, to tackle several GAN issues together, aiming for image generation with parsimonious prior knowledge. Through comprehensive evaluations across different datasets, we show that MIC-GANs are effective in structuring the latent space and avoiding mode collapse, and outperform state-of-the-art methods. MICGANs are adaptive, versatile, and robust. They offer a promising solution to several well-known GAN issues. Code available:github.com/yinghdb/MICGANs.

We propose a framework of efficient nonlinear deformable simulation with both fast continuous collision detection and robust collision resolution. We name this new framework Medial IPC as it integrates the merits from medial elastics, for an efficient and versatile reduced simulation, as well as incremental potential contact, for a robust collision and contact resolution. We leverage medial axis transform to construct a kinematic subspace. Instead of resorting to projective dynamics, we use classic hyperelastics to embrace real-world nonlinear materials. A novel reduced continuous collision detection algorithm is presented based on the medial mesh. Thanks to unique geometric properties of medial axis and medial primitives, we derive closed-form formulations for identifying between-primitive collision within the reduced medial space. In the meantime, the implicit barrier energy that generates necessary repulsion forces for collision resolution is also formulated with the medial coordinate. In other words, Medial IPC exploits a universal reduced coordinate for simulation, continuous self-/collision detection, and IPC-based collision resolution. Continuous collision detection also allows more aggressive time stepping. In addition, we carefully implement our system with a heterogeneous CPU-GPU deployment such that massively parallelizable computations are carried out on the GPU while few sequential computations are on the CPU. Such implementation also frees us from generating training poses for selecting Cubature points and pre-computing their weights. We have tested our method on complicated deformable models and collision-rich simulation scenarios. Due to the reduced nature of our system, the computation is faster than fullspace IPC or other fullspace methods using continuous collision detection by at least one order. The simulation remains high-quality as the medial subspace captures intriguing and local deformations with sufficient realism.

This paper provides a new avenue for exploiting deep neural networks to improve physics-based simulation. Specifically, we integrate the classic Lagrangian mechanics with a deep autoencoder to accelerate elastic simulation of deformable solids. Due to the inertia effect, the dynamic equilibrium cannot be established without evaluating the second-order derivatives of the deep autoencoder network. This is beyond the capability of off-the-shelf automatic differentiation packages and algorithms, which mainly focus on the gradient evaluation. Solving the nonlinear force equilibrium is even more challenging if the standard Newton's method is to be used. This is because we need to compute a third-order derivative of the network to obtain the variational Hessian. We attack those difficulties by exploiting complex-step finite difference, coupled with reverse automatic differentiation. This strategy allows us to enjoy the convenience and accuracy of complex-step finite difference and in the meantime, to deploy complex-value perturbations as collectively as possible to save excessive network passes. With a GPU-based implementation, we are able to wield deep autoencoders (e.g., 10+ layers) with a relatively high-dimension latent space in real-time. Along this pipeline, we also design a sampling network and a weighting network to enable weight-varying Cubature integration in order to incorporate nonlinearity in the model reduction. We believe this work will inspire and benefit future research efforts in nonlinearly reduced physical simulation problems.

Cloth dynamics and collision handling are the two most challenging topics in cloth simulation. While researchers have substantially improved the performances of cloth dynamics solvers recently, their success in fast collision detection and handling is rather limited. In this article, we focus our research on the safety, efficiency, and realism of the repulsion-based collision handling approach, which has demonstrated its potential in existing GPU-based simulators. Our first discovery is the necessary vertex distance conditions for cloth to enter self intersections, the negations of which can be viewed as vertex distance constraints continuous in time for sufficiently avoiding self collisions. Continuous constraints, however, cannot be enforced with ease. Our solution is to convert continuous constraints into three types of constraints: discrete edge length constraints, discrete vertex distance constraints, and vertex displacement constraints. Based on this solution, we develop a fast and safe collision handling process for enforcing constraints, a novel splitting method for integrating collision handling with dynamics solvers, and static and adaptive remeshing schemes to further improve the runtime performance. In summary, our cloth simulator is efficient, safe, robust, and parallelizable on a GPU. The experiment shows that it runs at least one order of magnitude faster than existing simulators.

This paper proposes a novel scalable image-based rendering (IBR) pipeline for indoor scenes with reflections. We make substantial progress towards three sub-problems in IBR, namely, depth and reflection reconstruction, view selection for temporally coherent view-warping, and smooth rendering refinements. First, we introduce a global-mesh-guided alternating optimization algorithm that robustly extracts a two-layer geometric representation. The front and back layers encode the RGB-D reconstruction and the reflection reconstruction, respectively. This representation minimizes the image composition error under novel views, enabling accurate renderings of reflections. Second, we introduce a novel approach to select adjacent views and compute blending weights for smooth and temporal coherent renderings. The third contribution is a supersampling network with a motion vector rectification module that refines the rendering results to improve the final output's temporal coherence. These three contributions together lead to a novel system that produces highly realistic rendering results with various reflections. The rendering quality outperforms state-of-the-art IBR or neural rendering algorithms considerably.

We present a computational design system that assists users to model, optimize, and fabricate quad-robots with soft skins. Our system addresses the challenging task of predicting their physical behavior by fully integrating the multibody dynamics of the mechanical skeleton and the elastic behavior of the soft skin. The developed motion control strategy uses an alternating optimization scheme to avoid expensive full space time-optimization, interleaving space-time optimization for the skeleton, and frame-by-frame optimization for the full dynamics. The output are motor torques to drive the robot to achieve a user prescribed motion trajectory. We also provide a collection of convenient engineering tools and empirical manufacturing guidance to support the fabrication of the designed quad-robot. We validate the feasibility of designs generated with our system through physics simulations and with a physically-fabricated prototype.

The emergence of COVID-19 has engendered a new wave of online hate speech in social media platforms such as Twitter. Its widespread effects range from acts of cyber-harassment towards certain ethnic communities (e.g., the Asian community), to targeting older people belonging to age groups correlated with higher mortality rates (termed infamously as "Boomer Remover"). Thus, an urgent need arises for a timely mitigation of this new wave of online hate speech. In this work, we aim to discover the hate-related keywords linked to COVID-19 in hateful tweets posted on Twitter so that users posting such keywords can be asked to reconsider posting them. We first collect a new dataset of tweets targeting older people supplementing with a dataset targeting the Asian community. Then, we develop an approach to analyze the datasets with BERT (a transformer-based model) attention mechanism and discover 186 novel keywords targeting the Asian community and 100 keywords targeting older people. Based on our study, we then propose a control mechanism wherein a user can be asked to reconsider using certain sensitive words identified by our approach. We further perform an exploratory analysis of BERT attention mechanism and find that the most high-impact, long distance attentions are learned in the earlier or later layers of the model depending on the underlying data distribution. Our study indicates that the BERT model in some cases uses a hate keyword and an associated group or individual to make predictions, a finding that is inline with existing hate-speech research, which suggests that hate-speech is often aimed at certain groups or individuals.

We propose a framework for the interactive simulation of nonlinear deformable objects. The primary feature of our system is the seamless integration of deformable simulation and collision culling, which are often independently handled in existing animation systems. The bridge connecting them is the medial axis transform (MAT), a high-fidelity volumetric approximation of complex 3D shapes. From the physics simulation perspective, MAT leads to an expressive and compact reduced nonlinear model. We employ a semireduced projective dynamics formulation, which well captures high-frequency local deformations of high-resolution models while retaining a low computation cost. Our key observation is that the most compelling (nonlinear) deformable effects are enabled by the local constraints projection, which should not be aggressively reduced, and only apply model reduction at the global stage. From the collision detection (CD)/collision culling (CC) perspective, MAT is geometrically versatile using linear-interpolated spheres (i.e., the so-called medial primitives (MPs)) to approximate the boundary of the input model. The intersection test between two MPs is formulated as a quadratically constrained quadratic program problem. We give an algorithm to solve this problem exactly, which returns the deepest penetration between a pair of intersecting MPs. When coupled with spatial hashing, collision (including self-collision) can be efficiently identified on the GPU within a few milliseconds even for massive simulations. We have tested our system on a variety of geometrically complex and high-resolution deformable objects, and our system produces convincing animations with all of the collisions/self-collisions well handled at an interactive rate.

NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g., an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though the neural network is known for its rich expressivity of nonlinear functions, directly using an NN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. NNWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model-the linear elasticity. In other words, NNWarp yields an incremental displacement fix per mesh node based on a simplified (therefore incorrect) simulation result other than synthesizing the unknown displacement directly. We introduce a compact yet effective feature vector including geodesic, potential and digression to sort training pairs of per-node linear and nonlinear displacement. NNWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one NN training is able to handle a wide range of 3D models of various geometries. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, which allows NNWarp to simulate large models in real time.

We present a novel spatial hashing based data structure to facilitate 3D shape analysis using convolutional neural networks (CNNs). Our method builds hierarchical hash tables for an input model under different resolutions that leverage the sparse occupancy of 3D shape boundary. Based on this data structure, we design two efficient GPU algorithms namely hash2col and col2hash so that the CNN operations like convolution and pooling can be efficiently parallelized. The perfect spatial hashing is employed as our spatial hashing scheme, which is not only free of hash collision but also nearly minimal so that our data structure is almost of the same size as the raw input. Compared with existing 3D CNN methods, our data structure significantly reduces the memory footprint during the CNN training. As the input geometry features are more compactly packed, CNN operations also run faster with our data structure. The experiment shows that, under the same network structure, our method yields comparable or better benchmark results compared with the state-of-the-art while it has only one-third memory consumption when under high resolutions (i.e., 2563).

In this paper, a deep learning (DL) framework was proposed to predict the taxi-passenger demand while the spatial, the temporal, and external dependencies were considered simultaneously. The proposed DL framework combined a modified density-based spatial clustering algorithm with noise (DBSCAN) and a conditional generative adversarial network (CGAN) model. More specifically, the modified DBSCAN model was applied to produce a number of sub-networks considering the spatial correlation of taxi pick-up events in the road network. And the CGAN model, fed with the historical taxi passenger demand and other conditional information, was capable to predict the taxi-passenger demands. The proposed CGAN model was made up with two long short-term memory (LSTM) neural networks, which are termed as the generative network G and the discriminative network D, respectively. Adversarial training process was conducted to the two LSTMs. In the numerical experiment, different model layouts were compared. It was found that different network layouts provided reasonable accuracy. With limited training data, more LSTM layers in the generator network resulted in not only higher accuracy, but also more difficulties in training. Comparisons were also conducted between the proposed prediction model and four typical approaches, including the moving average method, the autoregressive integrated moving method, the neural network model, and the LSTM neural network model. The comparison results showed that the proposed model outperformed all the other methods. And the repeated experiment indicated that the proposed CGAN model provided significant better predictions than the LSTM model did. Future research was recommended to include more datasets for testing the model and more information for improving predictive performance.

In deformable simulation, an important computing task is to calculate the gradient and derivative of the strain energy function in order to infer the corresponding internal force and tangent stiffness matrix. The standard numerical routine is the finite difference method, which evaluates the target function multiple times under a small real-valued perturbation. Unfortunately, the subtractive cancellation prevents us from setting this perturbation sufficiently small, and the regular finite difference is doomed for computing problems requiring a high-accuracy derivative evaluation. In this paper, we graft a new finite difference scheme, namely the complex-step finite difference (CSFD), with physics-based animation. CSFD is based on the complex Taylor series expansion, which avoids subtractions in first-order derivative approximation. As a result, one can use a very small perturbation to calculate the numerical derivative that is as accurate as its analytic counterpart. We accelerate the original CSFD method so that it is also as efficient as the analytic derivative. This is achieved by discarding high-order error terms, decoupling real and imaginary calculations, replacing costly functions based on the theory of equivalent infinitesimal, and isolating the propagation of the perturbation in composite/nesting functions. CSFD can be further augmented with multicomplex Taylor expansion and Cauchy-Riemann formula to handle higher-order derivatives and tensor-valued functions. We demonstrate the accuracy, convenience, and efficiency of this new numerical routine in the context of deformable simulation - one can easily deploy a robust simulator for general hyperelastic materials, including user-crafted ones to cater specific needs in different applications. Higher-order derivatives of the energy can be readily computed to construct modal derivative bases for reduced real-time simulation. Inverse simulation problems can also be conveniently solved using gradient/Hessian-based optimization procedures.

Abstract This paper presents a novel system that enables a fully automatic modeling of both 3D geometry and functionality of a mechanism assembly from a single RGB image. The resulting 3D mechanism model highly resembles the one in the input image with the geometry, mechanical attributes, connectivity, and functionality of all the mechanical parts prescribed in a physically valid way. This challenging task is realized by combining various deep convolutional neural networks to provide high‐quality and automatic part detection, segmentation, camera pose estimation and mechanical attributes retrieval for each individual part component. On the top of this, we use a local/global optimization algorithm to establish geometric interdependencies among all the parts while retaining their desired spatial arrangement. We use an interaction graph to abstract the inter‐part connection in the resulting mechanism system. If an isolated component is identified in the graph, our system enumerates all the possible solutions to restore the graph connectivity, and outputs the one with the smallest residual error. We have extensively tested our system with a wide range of classic mechanism photos, and experimental results show that the proposed system is able to build high‐quality 3D mechanism models without user guidance.

Abstract We investigate how to obtain high‐quality 360‐degree 3D reconstructions of small objects using consumer‐level depth cameras. For many homeware objects such as shoes and toys with dimensions around 0.06 – 0.4 meters, their whole projections, in the hand‐held scanning process, occupy fewer than 20% pixels of the camera's image. We observe that existing 3D reconstruction algorithms like KinectFusion and other similar methods often fail in such cases even under the close‐range depth setting. To achieve high‐quality 3D object reconstruction results at this scale, our algorithm relies on an online global non‐rigid registration, where embedded deformation graph is employed to handle the drifting of camera tracking and the possible nonlinear distortion in the captured depth data. We perform an automatic target object extraction from RGBD frames to remove the unrelated depth data so that the registration algorithm can focus on minimizing the geometric and photogrammetric distances of the RGBD data of target objects. Our algorithm is implemented using CUDA for a fast non‐rigid registration. The experimental results show that the proposed method can reconstruct high‐quality 3D shapes of various small objects with textures.

Pavement surface distress conditions are critical inputs for quantifying roadway infrastructure serviceability. Numerous computer-aided automatic examination techniques have been deployed for pavement distress condition assessments, such as digital image processing methods. However, their effectiveness and applicability are impeded due to information losses in 2-D image combination processes or extremely high costs in 3-D geo-referenced data set. In this paper, a cost-effective Kinect-based approach is proposed for 3-D pavement surface reconstruction and cracking recognition. We propose a comprehensive computational solution for the detection and recognition of pavement distress feature identification. Various cracking measurements such as alligator cracking, traverse cracking, longitudinal cracking, and so on. are identified and recognized for their severity examinations based on associated geometrical features. The experimental results indicate that this method is effective in reducing data collection costs and extracting analytical information on pavement cracking measurements. The research findings confirm that the proposed approach provides a viable, applicable solution to an automatic pavement surface condition detection and evaluation. The proposed methodology is transferable for pavement surface reconstruction and distress condition detection based on the other 3-D cloud point data. It provides an alternative inexpensive complement to existing pavement examination methodologies.

Recent technology advances significantly push forward the development and the deployment of the concept of smart, such as smart community and smart city. Smart transportation is one of the core components in modern urbanization processes. Under this context, the connected autonomous vehicle (CAV) system presents a promising solution towards the enhanced traffic safety and mobility through state-of-the-art wireless communications and autonomous driving techniques. Being capable of collecting and transmitting real-time vehicle-specific, location-specific, and area-wide traffic information, it is believed that CAV-enabled transportation systems will revolutionize the existing understanding of network-wide traffic operations and reestablish traffic flow theory. This paper develops a new continuum dynamics model for the future CAV-enabled traffic system, realized by encapsulating mutually-coupled vehicle interactions using virtual internal and external forces. Leveraging Newton's second law of motion, our model naturally preserves the traffic volume and automatically handles both the longitudinal and lateral traffic operations due to its 2-D nature, which sets us apart from the existing macroscopic traffic flow models. Our model can also be rolled back to handle the conventional traffic of human drivers, and the experiment shows that the model describes real-world traffic behavior well. Therefore, we consider the proposed model a complement and generalization of the existing traffic theory. We also develop a smoothed particle hydrodynamics-based numerical simulation and an interactive traffic visualization framework. By posing user-specified external constraints, our system allows users to visually understand the impact of different traffic operations interactively.

This paper presents a spatial reduction framework for simulating nonlinear deformable objects interactively. This reduced model is built using a small number of overlapping quadratic domains as we notice that incorporating high-order degrees of freedom (DOFs) is important for the simulation quality. Departing from existing multi-domain methods in graphics, our method interprets deformed shapes as blended quadratic transformations from nearby domains. Doing so avoids expensive safeguards against the domain coupling and improves the numerical robustness under large deformations. We present an algorithm that efficiently computes weight functions for reduced DOFs in a physics-aware manner. Inspired by the well-known multi-weight enveloping technique, our framework also allows subspace tweaking based on a few representative deformation poses. Such elastic weighting mechanism significantly extends the expressivity of the reduced model with light-weight computational efforts. Our simulator is versatile and can be well interfaced with many existing techniques. It also supports local DOF adaption to incorporate novel deformations (i.e., induced by the collision). The proposed algorithm complements state-of-the-art model reduction and domain decomposition methods by seeking for good trade-offs among animation quality, numerical robustness, pre-computation complexity, and simulation efficiency from an alternative perspective.

We propose an acoustic-VR system that converts acoustic signals of human language (Chinese) to realistic 3D tongue animation sequences in real time. It is known that directly capturing the 3D geometry of the tongue at a frame rate that matches the tongue's swift movement during the language production is challenging. This difficulty is handled by utilizing the electromagnetic articulography (EMA) sensor as the intermediate medium linking the acoustic data to the simulated virtual reality. We leverage Deep Neural Networks to train a model that maps the input acoustic signals to the positional information of pre-defined EMA sensors based on 1,108 utterances. Afterwards, we develop a novel reduced physics-based dynamics model for simulating the tongue's motion. Unlike the existing methods, our deformable model is nonlinear, volume-preserving, and accommodates collision between the tongue and the oral cavity (mostly with the jaw). The tongue's deformation could be highly localized which imposes extra difficulties for existing spectral model reduction methods. Alternatively, we adopt a spatial reduction method that allows an expressive subspace representation of the tongue's deformation. We systematically evaluate the simulated tongue shapes with real-world shapes acquired by MRI/CT. Our experiment demonstrates that the proposed system is able to deliver a realistic visual tongue animation corresponding to a user's speech signal.

Abstract We present an approach to fabricate shell objects with thickness parameters, which are computed to maintain the user‐specified structural stability. Given a boundary surface and user‐specified external forces, we optimize the thickness parameters according to stress constraints to extrude the surface. Our approach mainly consists of two technical components: First, we develop a patch‐based shell simulation technique to efficiently support the static simulation of extruded shell objects using finite element methods. Second, we analytically compute the derivative of stress required in the sensitivity analysis technique to turn the optimization into a sequential linear programming problem. Experimental results demonstrate that our approach can optimize the thickness parameters for arbitrary surfaces in a few minutes and well predict the physical properties, such as the deformation and stress of the fabricated object.

This article describes a contour-based 3D tongue deformation visualization framework using B-mode ultrasound image sequences. A robust, automatic tracking algorithm characterizes tongue motion via a contour, which is then used to drive a generic 3D Finite Element Model (FEM). A novel contour-based 3D dynamic modeling method is presented. Modal reduction and modal warping techniques are applied to model the deformation of the tongue physically and efficiently. This work can be helpful in a variety of fields, such as speech production, silent speech recognition, articulation training, speech disorder study, etc.

Inferring the functionality of an object from a single RGBD image is difficult for two reasons: lack of semantic information about the object, and missing data due to occlusion. In this paper, we present an interactive framework to recover a 3D functional prototype from a single RGBD image. Instead of precisely reconstructing the object geometry for the prototype, we mainly focus on recovering the object’s functionality along with its geometry. Our system allows users to scribble on the image to create initial rough proxies for the parts. After user annotation of high-level relations between parts, our system automatically jointly optimizes detailed joint parameters (axis and position) and part geometry parameters (size, orientation, and position). Such prototype recovery enables a better understanding of the underlying image geometry and allows for further physically plausible manipulation. We demonstrate our framework on various indoor objects with simple or hybrid functions.

In this paper, we present an interactive system for mechanism modeling from multi-view images. Its key feature is that the generated 3D mechanism models contain not only geometric shapes but also internal motion structures: they can be directly animated through kinematic simulation. Our system consists of two steps: interactive 3D modeling and stochastic motion parameter estimation. At the 3D modeling step, our system is designed to integrate the sparse 3D points reconstructed from multi-view images and a sketching interface to achieve accurate 3D modeling of a mechanism. To recover the motion parameters, we record a video clip of the mechanism motion and adopt stochastic optimization to recover its motion parameters by edge matching. Experimental results show that our system can achieve the 3D modeling of a range of mechanisms from simple mechanical toys to complex mechanism objects.

We show that many existing elastic body simulation approaches can be interpreted as descent methods, under a nonlinear optimization framework derived from implicit time integration. The key question is how to find an effective descent direction with a low computational cost. Based on this concept, we propose a new gradient descent method using Jacobi preconditioning and Chebyshev acceleration. The convergence rate of this method is comparable to that of L-BFGS or nonlinear conjugate gradient. But unlike other methods, it requires no dot product operation, making it suitable for GPU implementation. To further improve its convergence and performance, we develop a series of step length adjustment, initialization, and invertible model conversion techniques, all of which are compatible with GPU acceleration. Our experiment shows that the resulting simulator is simple, fast, scalable, memory-efficient, and robust against very large time steps and deformations. It can correctly simulate the deformation behaviors of many elastic materials, as long as their energy functions are second-order differentiable and their Hessian matrices can be quickly evaluated. For additional speedups, the method can also serve as a complement to other techniques, such as multi-grid.

In this paper, we present a framework allowing users to interact with geometrically complex 3D deformable objects using (multiple) haptic devices based on an extended shape matching approach. There are two major challenges for haptic-enabled interaction using the shape matching method. The first is how to obtain a rapid deformation propagation when a large number of shape matching clusters exist. The second is how to robustly handle the collision response when the haptic interaction point hits the particle-sampled deformable volume. Our framework extends existing multi-resolution shape matching methods, providing an improved energy convergence rate. This is achieved by using adaptive integration strategies to avoid insignificant shape matching iterations during the simulation. Furthermore, we present a new mechanism called stable constraint particle coupling which ensures consistent deformable behavior during haptic interaction. As demonstrated in our experimental results, the proposed method provides natural and smooth haptic rendering as well as efficient yet stable deformable simulation of complex models in real time.

Model reduction has popularized itself for simulating elastic deformation for graphics applications. While these techniques enjoy orders-of-magnitude speedups at runtime simulation, the efficiency of precomputing reduced subspaces remains largely over-looked. We present a complete system of precomputation pipeline as a faster alternative to the classic linear and nonlinear modal analysis. We identify three bottlenecks in the traditional model reduction precomputation, namely modal matrix construction, cubature training, and training dataset generation, and accelerate each of them. Even with complex deformable models, our method has achieved orders-of-magnitude speedups over the traditional precomputation steps, while retaining comparable runtime simulation quality.

Cardiopulmonary resuscitation (CPR) plays a primary role in first-aid treatment. Instead of the traditional instructor-led training course, we propose a virtual reality system which provides an immersive 3D environment for CPR training with visual and haptic feedback. To simulate a real world CPR experience, our immersive trainer system enables a trainee to perform CPR compressions to a virtual human, inside the virtual world. During the training procedure, the trainee can not only watch his/her 3D image performing CPR, but also feel the force feedback from the chest compressions in real-time. To further enhance the visual fidelity, a haptic-enabled deformable model is applied to show the visual change of chest during compression.

In this paper, we propose a novel multimedia system adaptively streaming the animation according to display resolution and/or network bandwidth. A Multigrid-like technique is used in this framework to accelerate the converging rate of the optimization of the nonlinear deformation energy. The computation is performed from coarsest mesh at the top level to the finest mesh at the bottom level and then goes back to the top again. Such V-shape calculation provides great flexibility for the networked environment. Clients are able to receive the data streaming corresponding to its display resolution and network bandwidth. A more compact form of deformation data packaging is also used in this system such that a cube element only needs six parameters instead of 24 variables as used in regular mesh representation, which significantly reduces the network overhead for the streaming.

In this paper, a physics-based framework is presented to visualize the human tongue deformation. The tongue is modeled with the Finite Element Method (FEM) and driven by the motion capture data gathered during speech production. Several novel deformation visualization techniques are presented for in-depth data analysis and exploration. To reveal the hidden semantic information of the tongue deformation, we present a novel physics-based volume segmentation algorithm. This is accomplished by decomposing the tongue model into segments based on its deformation pattern with the computation of deformation subspaces and fitting the target deformation locally at each segment. In addition, the strain energy is utilized to provide an intuitive low-dimensional visualization for the high-dimensional sequential motion. Energy-interpolation-based morphing is also equipped to effectively highlight the subtle differences of the 3D deformed shapes without any visual occlusion. Our experimental results and analysis demonstrate the effectiveness of this framework. The proposed methods, though originally designed for the exploration of the tongue deformation, are also valid for general deformation analysis of other shapes.

In this paper, we propose a novel framework for multidomain subspace deformation using node-wise corotational elasticity. With the proper construction of subspaces based on the knowledge of the boundary deformation, we can use the Lagrange multiplier technique to impose coupling constraints at the boundary without overconstraining. In our deformation algorithm, the number of constraint equations to couple two neighboring domains is not related to the number of the nodes on the boundary but is the same as the number of the selected boundary deformation modes. The crack artifact is not present in our simulation result, and the domain decomposition with loops can be easily handled. Experimental results show that the single-core implementation of our algorithm can achieve real-time performance in simulating deformable objects with around quarter million tetrahedral elements.

Fast and accurate simulation of 3D soft objects is important to virtual environment and reality. Simulating 3D deformation of large model in real-time is a challenging problem as it is very computation-demanding involving intensive matrix-based operation of large scale. Reduction techniques, consequently flourish where the dynamic is computed within a subspace of much smaller size with accuracy loss. This type of technique greatly boosts the simulation performance. Currently, most reduction methods use globally-computed bases. As a result, when large local deformation occurs, global bases often fail to provide necessary freedoms at the desired region. Alternatively, we construct subspaces locally based on the linear component mode synthesis (CMS) method. The components are the mutually disjoint sub-meshes (with duplicated boundary DOFs) and the local bases are called component modes which are the displacements of the components under certain mechanical equilibrium.We greatly extend the classic CMS with the following contributions. 1) We propose a new physics-based multi-domain subspace deformable model based on CMS. The subspace is locally constructed with component modes. The computation of modes follow a compact and straightforward formulation and the pre-computation is orders-faster comparing with some global subspace techniques. 2) The classic CMS does not handle large deformations with the linear modes. We extend the idea of modal warping to CMS with co-rotational elasticity to accommodate large rotational deformation. 3) A new type of mode called degenerated constraint mode is employed which constructs the subspaces of small size at components while preserving the boundary compatibility. As a result, the simulation can be performed within a small subspace and the boundary locking artifacts are also avoided. 4) We also propose another new type of mode called user constraint mode, which prevents the reduced system from being over-constrained. 5) Based on the extended CMS, we propose several simulation strategies including the hybrid simulation with the customized local mode supersets and the skeleton-driven deformable model based on the interface hierarchy.

We presents a spectral approach to simulate hybrid objects with deformable and rigid materials in real time. This framework is able to handle large-scale model under the help of GPU's parallel computation.

Abstract A novel framework is proposed in this paper to simulate hybrid solids with deformable and rigid materials in real‐time. Both types of materials are uniformly integrated into one spectral simulator. Based on the modal warping technique, we employ a new constraint strategy which eliminates the accumulation of approximation errors at the boundary interfaces, thus naturally gluing different materials. We also utilize the GPU to accelerate the run‐time computation when updating the geometry of the hybrid solid—the most expensive step in this framework. This work provides a general‐purpose solution of simulating hybrid objects in real‐time, even for large‐scale models. Copyright © 2010 John Wiley & Sons, Ltd.