arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

Gen2Physics:通过多视图材料分解将生成的三维网格与物理特性关联

Gen2Physics: Grounding Generated 3D Meshes in Physics via Multi-View Material Decomposition

Mauro Comi, Jordi Serrano Berbel, Kevis-Kokitsi Maninis, Philipp Henzler, Manuel Sanchez

arXiv 2608.23869首次发表:更新:

发表机构

University of Bristol; Google DeepMind; Google Research(布里斯托大学; 谷歌DeepMind; 谷歌研究院)

机构由 AI 辅助整理,请以论文原文为准。

AI 中文总结

Gen2Physics是一个将生成的三维网格与物理特性关联的自动化框架,通过多视图材料分解实现,其材料分割精度较现有方法提升超一倍,还能输出水密性各材料子网格。

AI 中文摘要

尽管当前最先进的生成模型能生成高保真的三维网格,但这些输出缺乏交互式模拟、游戏或机器人技术所需的物理特性。我们提出Gen2Physics,这是一个统一的自动化框架,通过自动将生成的网格分解为其组成材料部件,使这些网格与物理特性关联。与专注于与标准物理引擎不兼容的体积表示的现有方法不同,Gen2Physics直接在网格上操作,以生成可立即用于模拟的资产。我们的流程集成了一个用于密集材料分割的微调Vision Transformer、一个稳健的二维到三维一致性投影,以及一个利用上下文推理来分配物理特性并推断内部几何结构(实心与空心)的视觉语言模型(VLM)。通过将表面面片转换为具有不同密度的体积,我们的方法能够实现物理上合理的动态模拟。在ABO-500和PartNet-Material基准上的实验结果表明,Gen2Physics的材料分割精度是现有物理关联流程的两倍以上(从15.6提升至48.3 mIoU),同时达到了体积方法的质量估计精度,并且是唯一能输出水密性各材料子网格的方法。

英文摘要

While state-of-the-art generative models produce high-fidelity 3D meshes, these outputs lack the physical properties required for interactive simulation, gaming, or robotics. We introduce Gen2Physics, a unified and automated framework that grounds generated meshes in physics by automatically decomposing them into their constituent material components. Unlike prior approaches, which focus on volumetric representations incompatible with standard physics engines, Gen2Physics operates directly on meshes to produce immediately simulation-ready assets. Our pipeline integrates a fine-tuned Vision Transformer for dense material segmentation, a robust 2D-to-3D consistency projection, and a Vision-Language Model (VLM) guided refinement that leverages contextual reasoning to assign physical properties and infer internal geometry (solid vs. hollow). By converting surface patches into volumes with distinct densities, our method enables physically plausible dynamic simulations. Experimental results on the ABO-500 and PartNet-Material benchmarks demonstrate that Gen2Physics more than doubles the material segmentation accuracy of prior physics-grounding pipelines (15.6 to 48.3 mIoU), while matching the mass-estimation accuracy of volumetric methods and being the only approach to output watertight per-material sub-meshes.

论文原文

arXiv 摘要页 · PDF 原文 · HTML 原文

↑