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

TL;DR

MotionAnymesh is a zero-shot framework that converts static 3D meshes into physically grounded, collision-free, and simulation-ready digital twins for embodied AI and robotics, addressing previous limitations of hallucinations and mesh inter-penetration.

Contribution

It introduces a kinematic-aware segmentation and a physics-constrained joint estimation pipeline, enabling automatic, reliable, and physically plausible digital twin creation from static meshes.

Findings

Outperforms state-of-the-art methods in geometric accuracy

Ensures collision-free articulation for simulation

Produces assets suitable for downstream embodied AI applications

Abstract

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.