用3D高斯点建模可动物体，让各部件运动更真实稳定。
Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting
- 通过可学习属性的部件感知高斯表示，实现结构化变形。
- 在真实和合成数据上，可动部件的重建误差降低10倍。
- 引入斥力场防止部件碰撞，适合机器人、动画等场景。
可动物体在现实世界中普遍存在，但其结构与运动的3D重建仍是难题。本文提出Part²GS，一种用于多部件物体高保真数字孪生建模的新框架，具备精确几何与物理一致的运动特性。该方法采用部件感知的3D高斯表示，通过可学习属性编码各组件，实现结构化且解耦的形变，保持高保真几何。为确保运动物理一致性，设计基于物理约束的运动感知规范表示，包含接触强制、速度一致性及向量场对齐。此外，引入斥力点场防止部件碰撞，显著提升运动连贯性。在合成与真实数据集上的广泛评估显示，Part²GS在可动部件的Chamfer Distance上相比最先进方法最高提升10倍。
原文摘要 · Abstract (English)
Articulated objects are common in the real world, yet modeling their structure and motion remains a challenging task for 3D reconstruction methods. In this work, we introduce Part$^{2}$GS, a novel framework for modeling articulated digital twins of multi-part objects with high-fidelity geometry and physically consistent articulation. Part$^{2}$GS leverages a part-aware 3D Gaussian representation that encodes articulated components with learnable attributes, enabling structured, disentangled transformations that preserve high-fidelity geometry. To ensure physically consistent motion, we propose a motion-aware canonical representation guided by physics-based constraints, including contact enforcement, velocity consistency, and vector-field alignment. Furthermore, we introduce a field of repel points to prevent part collisions and maintain stable articulation paths, significantly improving motion coherence over baselines. Extensive evaluations on both synthetic and real-world datasets show that Part$^{2}$GS consistently outperforms state-of-the-art methods by up to 10$\times$ in Chamfer Distance for movable parts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。