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

2026-03-13

AI Summary

This work addresses the challenge of transforming static 3D meshes into interactive, simulation-ready digital twins, a task often hindered by kinematic hallucinations and self-collisions due to the neglect of physical constraints in existing approaches. To overcome this, the authors propose MotionAnymesh—a zero-shot automated framework that integrates SP4D physical priors with vision-language models to achieve kinematics-aware part segmentation and joint-type recognition. Building upon this semantic understanding, the method further enforces geometric and physical constraints to initialize joint parameters and optimize motion trajectories, ensuring collision-free and dynamically feasible results. Experimental evaluations demonstrate that MotionAnymesh significantly outperforms current methods in both geometric accuracy and physical plausibility, enabling efficient generation of high-fidelity, simulation-ready digital twin assets.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Motion and Path Planning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

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.

Problem

• articulated assets
• kinematic hallucinations
• mesh inter-penetration
• physical simulation
• digital twins

Innovation

• physics-grounded articulation
• zero-shot digital twin
• kinematic-aware segmentation
• collision-free joint estimation
• SP4D physical priors