Real-Time Physics Simulation with Dynamic Mesh-Gaussian Reconstructions 文章

ArXiv CS.CV2026-06-02NEWSen作者: Adrian Ramlal, John S. Zelek

摘要

arXiv:2606.00444v1 Announce Type: new Abstract: Integrating dynamic 3D reconstructions into physics simulation requires fixed mesh topology for efficient collision detection, but state-of-the-art methods like DG-Mesh produce varying topology optimized for geometric quality. We investigate whether topology conversion can enable physics integration while preserving reconstruction fidelity. We propose a dual-representation framework combining fixed-topology meshes for physics with Gaussian splatting for rendering, achieving 4.65$\times$ speedup over varying-topology baselines through runtime vertex buffer updates. We evaluate two conversion strategies, temporal correspondence tracking and template-based projection, against native fixed-topology methods (MaGS) on the DG-Mesh dataset. Our evaluation reveals that both conversion approaches incur 65-80% geometric degradation, producing results inferior to MaGS despite DG-Mesh's superior initial quality.

相关公司

暂无数据

相关人物

暂无数据

相关产品

暂无数据