MotionAnymesh: 物理に基づく関節構造生成によるシミュレーション対応デジタルツイン
MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins
静的な3Dメッシュを、物理シミュレーションで動作可能な関節付きアセットへ自動変換するフレームワークを提案。VLMの推論に物理的知識を組み込み、関節推定と衝突回避を最適化する。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: WenBo Xu, Liu Liu, Li Zhang, Dan Guo, RuoNan Liu
分類: cs.RO, cs.CV
原文アブストラクト
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.
