AI RESEARCH

MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins

arXiv CS.CV

ArXi:2603.12936v1 Announce Type: cross 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.