MotionAnymesh：基于物理的运动模拟数字双胞胎生成
MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins
AI总结：
本文提出MotionAnymesh框架，通过结合物理先验知识和几何物理联合估计，解决静态3D网格转化为可交互数字双胞胎的难题，提升模拟精度和物理可行性。
摘要：
将静态3D网格转换为可交互的运动资产对具身AI和机器人仿真至关重要。然而，现有零样本流程在处理复杂资产时面临关键问题，即缺乏物理基础。具体而言，未加约束的视觉-语言模型（VLMs）常出现运动学幻觉，而无约束的关节估计会导致物理仿真中的网格穿透。为弥合这一差距，我们提出MotionAnymesh，一种自动化零样本框架，能够无缝地将无结构静态网格转换为仿真准备的数字双胞胎。我们的方法包含一个运动学感知的部分分割模块，通过显式SP4D物理先验知识来约束VLM推理，有效消除运动学幻觉。此外，我们引入了一个几何-物理联合估计流程，结合稳健的类型感知初始化和受物理约束的轨迹优化，严格保证碰撞自由的运动。大量实验表明，MotionAnymesh在几何精度和动态物理可执行性方面均显著优于现有最先进基线，为下游应用提供了高度可靠的资产。
英文摘要：
Converting static 3D meshes into interactable articulated assets is crucial for embodied AI and robotic simulation. However, existing zero-shot pipelines struggle with complex assets due to a critical lack of physical grounding. Specifically, ungrounded Vision-Language Models (VLMs) frequently suffer from kinematic hallucinations, while unconstrained joint estimation inevitably leads to catastrophic mesh inter-penetration during physical simulation. To bridge this gap, we propose MotionAnymesh, an automated zero-shot framework that seamlessly transforms unstructured static meshes into simulation-ready digital twins. Our method features a kinematic-aware part segmentation module that grounds VLM reasoning with explicit SP4D physical priors, effectively eradicating kinematic hallucinations. Furthermore, we introduce a geometry-physics joint estimation pipeline that combines robust type-aware initialization with physics-constrained trajectory optimization to rigorously guarantee collision-free articulation. Extensive experiments demonstrate that MotionAnymesh significantly outperforms state-of-the-art baselines in both geometric precision and dynamic physical executability, providing highly reliable assets for downstream applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
