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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Tianjiao, Shah, Vedant, Wahed, Muntasir, Shen, Ying, Nguyen, Kiet A., Lourentzou, Ismini
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918436041392128
author Yu, Tianjiao
Shah, Vedant
Wahed, Muntasir
Shen, Ying
Nguyen, Kiet A.
Lourentzou, Ismini
author_facet Yu, Tianjiao
Shah, Vedant
Wahed, Muntasir
Shen, Ying
Nguyen, Kiet A.
Lourentzou, Ismini
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17212
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting
Yu, Tianjiao
Shah, Vedant
Wahed, Muntasir
Shen, Ying
Nguyen, Kiet A.
Lourentzou, Ismini
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Robotics
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.
title Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Robotics
url https://arxiv.org/abs/2506.17212