Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting

TL;DR

Part$^{2}$GS is a new framework for modeling articulated objects with high-fidelity geometry and physically consistent motion using a part-aware 3D Gaussian representation and physics-based constraints.

Contribution

It introduces a novel part-aware 3D Gaussian model with a motion-aware canonical representation and collision prevention for improved articulated object reconstruction.

Findings

Outperforms state-of-the-art methods by up to 10× in Chamfer Distance.

Effectively models both synthetic and real-world articulated objects.

Ensures physically consistent motion with contact, velocity, and vector-field constraints.

Abstract

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.