Real-Time Cloth Simulation Using WebGPU: Evaluating Limits of High-Resolution

TL;DR

This paper demonstrates that WebGPU can efficiently perform high-resolution real-time cloth simulation, significantly outperforming WebGL and handling complex collision detection within strict frame rate constraints.

Contribution

It introduces a WebGPU-based cloth simulation system using the Mass-Spring Method, showcasing its superior performance and real-time capabilities for high-resolution models.

Findings

WebGPU outperforms WebGL in high-resolution cloth simulations

Real-time collision detection is feasible with up to 100k cloth nodes

Maintains 60 fps with models up to 640K nodes

Abstract

This study explores the capabilities of WebGPU, an emerging web graphics paradigm, for real-time cloth simulation. Traditional WebGL-based methods have been in handling complex physical simulations due to their emphasis on graphics rendering rather than general-purpose GPU (GPGPU) operations. WebGPU, designed to provide modern 3D graphics and computational capabilities, offers significant improvements through parallel processing and support for computational shaders. In this work, we implemented a cloth simulation system using the Mass-Spring Method within the WebGPU framework, integrating collision detection and response handling with the 3D surface model. First, comparative performance evaluations demonstrate that WebGPU substantially outperforms WebGL, particularly in high-resolution simulations, maintaining 60 frames per second (fps) even with up to 640K nodes. The second experiment aimed to determine the real-time limitations of WebGPU and confirmed that WebGPU can handle real-time collisions between 4K and 100k cloth node models and a 100K triangle surface model in real-time. These experiments also highlight the importance of balancing real-time performance with realistic rendering when handling collisions between cloth models and complex 3D objects. Our source code is available at https://github.com/nakjun/Cloth-Simulation-WebGPU