Part$^{2}$GS：基于 3D 高斯泼溅的关节物体部件感知建模
Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting
把 3DGS 的每个高斯绑定可学习部件属性，配合接触约束、速度一致性与斥力点场实现物理一致的关节运动，可直接迁移到可动物体/机器人场景的数字孪生与可动部件重建。
原文依据 a part-aware 3D Gaussian representation that encodes articulated components with learnable attributes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论关节物体在真实世界中十分常见，但对其结构与运动进行建模对三维重建方法而言仍是一项具有挑战性的任务。本文提出 Part$^{2}$GS，一种用于建模多部件物体关节式数字孪生的新框架，兼具高保真几何与物理一致的关节运动。Part$^{2}$GS 利用部件感知的 3D 高斯表示，将关节部件编码为带有可学习属性的形式，从而实现结构化、解耦的变换并保持高保真几何。为确保物理一致的运动，我们提出一种由基于物理的约束引导的运动感知规范表示，这些约束包括接触约束、速度一致性与向量场对齐。此外，我们引入斥力点场以防止部件碰撞并维持稳定的关节运动路径，相比基线显著提升了运动连贯性。在合成与真实数据集上的大量评测表明，Part$^{2}$GS 在可动部件上以最高达 10 倍的 Chamfer 距离持续优于最优方法。
英文原文摘要 1114 字符
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 10xin Chamfer Distance for movable parts.