Bi-Stride Multi-Scale Graph Neural Network for Mesh-Based Physical Simulation

Cao, Yadi; Chai, Menglei; Li, Minchen; Jiang, Chenfanfu

doi:10.48550/arxiv.2210.02573

Cited by 2 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input character mesh is first processed into a hierarchically nested multi-scale resolution structure: for finer resolution meshes, any vertex is selected as the central point, and vertices with even adjacency are extracted to form the next level's coarser mesh. These vertices are connected with what we refer to as bi-stride structured edges, 25 termed coarsening edges. This iterative process ultimately results in a multi-layered nested graph, where a series of coarsening edge sets share the same set of nodes.…”

Section: Msea-mg Blockmentioning

confidence: 99%

Multi‐scale edge aggregation mesh‐graph‐network for character secondary motion

Wang,

Liu

2024

Computer Animation & Virtual

View full text Add to dashboard Cite

As an enhancement to skinning‐based animations, light‐weight secondary motion method for 3D characters are widely demanded in many application scenarios. To address the dependence of data‐driven methods on ground truth data, we propose a self‐supervised training strategy that is free of ground truth data for the first time in this domain. Specifically, we construct a self‐supervised training framework by modeling the implicit integration problem with steps as an optimization problem based on physical energy terms. Furthermore, we introduce a multi‐scale edge aggregation mesh‐graph block (MSEA‐MG Block), which significantly enhances the network performance. This enables our model to make vivid predictions of secondary motion for 3D characters with arbitrary structures. Empirical experiments indicate that our method, without requiring ground truth data for model training, achieves comparable or even superior performance quantitatively and qualitatively compared to state‐of‐the‐art data‐driven approaches in the field.

show abstract

Section: Msea-mg Blockmentioning

confidence: 99%

Multi‐scale edge aggregation mesh‐graph‐network for character secondary motion

Wang,

Liu

2024

Computer Animation & Virtual

View full text Add to dashboard Cite

show abstract

“…Researchers have proposed some excellent approaches to predict fluid behaviors. Famous data-driven methods include regression forests [21], Fully Connected Neural Networks (FCNN) [22], [23], [24], Convolutional Neural Networks (CNN) [25], [26], [27], [28], Continuous Convolutional Neural Networks [29], [30], Recurrent Neural Networks (RNN) [31], [32], Graph Neural Networks (GNN) [33], [34], Generated Adversarial Networks (GAN) [35], [36], etc. However, little attention has arXiv:2305.03315v1 [cs.GR] 5 May 2023 been paid to tackling fluid and solid's two-way interactions since different materials' properties and interacting forces are coupled in a complicated dynamic system.…”

Section: Introductionmentioning

confidence: 99%

MPMNet: A Data-Driven MPM Framework for Dynamic Fluid-Solid Interaction

Gao

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

High-accuracy, high-efficiency physics-based fluid-solid interaction is essential for reality modeling and computer animation in online games or real-time Virtual Reality (VR) systems. However, the large-scale simulation of incompressible fluid and its interaction with the surrounding solid environment is either time-consuming or suffering from the reduced time/space resolution due to the complicated iterative nature pertinent to numerical computations of involved Partial Differential Equations (PDEs). In recent years, we have witnessed significant growth in exploring a different, alternative data-driven approach to addressing some of the existing technical challenges in conventional model-centric graphics and animation methods. This paper showcases some of our exploratory efforts in this direction. One technical concern of our research is to address the central key challenge of how to best construct the numerical solver effectively and how to best integrate spatiotemporal/dimensional neural networks with the available MPM's pressure solvers. In particular, we devise the MPMNet, a hybrid data-driven framework supporting the popular and powerful Material Point Method (MPM), to combine the comprehensive properties of MPM in numerically handling physical behaviors ranging from fluid to deformable solids and the high efficiency of data-driven models. At the architectural level, our MPMNet comprises three primary components: A data processing module to describe the physical properties by way of the input fields; A deep neural network group to learn the spatiotemporal features; And an iterative refinement process to continue to reduce possible numerical errors. The goal of these special technical developments is to aim at involved numerical acceleration while preserving physical accuracy, realizing efficient and accurate fluid-solid interactions in a data-driven fashion. The extensive experimental results verify that our MPMNet can tremendously speed up the computation compared with the popular numerical methods as the complexity of interaction scenes increases while better retaining the numerical accuracy.

show abstract

Bi-Stride Multi-Scale Graph Neural Network for Mesh-Based Physical Simulation

Cited by 2 publications

References 19 publications

Multi‐scale edge aggregation mesh‐graph‐network for character secondary motion

Multi‐scale edge aggregation mesh‐graph‐network for character secondary motion

MPMNet: A Data-Driven MPM Framework for Dynamic Fluid-Solid Interaction

Contact Info

Product

Resources

About