Saved in:
Bibliographic Details
Main Authors: Wang, Haowen, Yuan, Xiaoping, Jin, Zhao, Zhao, Zhen, Che, Zhengping, Xue, Yousong, Tian, Jin, Huang, Yakun, Tang, Jian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.09663
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914359960141824
author Wang, Haowen
Yuan, Xiaoping
Jin, Zhao
Zhao, Zhen
Che, Zhengping
Xue, Yousong
Tian, Jin
Huang, Yakun
Tang, Jian
author_facet Wang, Haowen
Yuan, Xiaoping
Jin, Zhao
Zhao, Zhen
Che, Zhengping
Xue, Yousong
Tian, Jin
Huang, Yakun
Tang, Jian
contents Articulated objects are ubiquitous and important in robotics, AR/VR, and digital twins. Most self-supervised methods for articulated object modeling reconstruct discrete interaction states and relate them via cross-state geometric consistency, yielding representational fragmentation and drift that hinder smooth control of articulated configurations. We introduce PD$^{2}$GS, a novel framework that learns a shared canonical Gaussian field and models the arbitrary interaction state as its continuous deformation, jointly encoding geometry and kinematics. By associating each interaction state with a latent code and refining part boundaries using generic vision priors, PD$^{2}$GS enables accurate and reliable part-level decoupling while enforcing mutual exclusivity between parts and preserving scene-level coherence. This unified formulation supports part-aware reconstruction, fine-grained continuous control, and accurate kinematic modeling, all without manual supervision. To assess realism and generalization, we release RS-Art, a real-to-sim RGB-D dataset aligned with reverse-engineered 3D models, supporting real-world evaluation. Extensive experiments demonstrate that PD$^{2}$GS surpasses prior methods in geometric and kinematic accuracy, and in consistency under continuous control, both on synthetic and real data.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09663
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PD$^{2}$GS: Part-Level Decoupling and Continuous Deformation of Articulated Objects via Gaussian Splatting
Wang, Haowen
Yuan, Xiaoping
Jin, Zhao
Zhao, Zhen
Che, Zhengping
Xue, Yousong
Tian, Jin
Huang, Yakun
Tang, Jian
Computer Vision and Pattern Recognition
Articulated objects are ubiquitous and important in robotics, AR/VR, and digital twins. Most self-supervised methods for articulated object modeling reconstruct discrete interaction states and relate them via cross-state geometric consistency, yielding representational fragmentation and drift that hinder smooth control of articulated configurations. We introduce PD$^{2}$GS, a novel framework that learns a shared canonical Gaussian field and models the arbitrary interaction state as its continuous deformation, jointly encoding geometry and kinematics. By associating each interaction state with a latent code and refining part boundaries using generic vision priors, PD$^{2}$GS enables accurate and reliable part-level decoupling while enforcing mutual exclusivity between parts and preserving scene-level coherence. This unified formulation supports part-aware reconstruction, fine-grained continuous control, and accurate kinematic modeling, all without manual supervision. To assess realism and generalization, we release RS-Art, a real-to-sim RGB-D dataset aligned with reverse-engineered 3D models, supporting real-world evaluation. Extensive experiments demonstrate that PD$^{2}$GS surpasses prior methods in geometric and kinematic accuracy, and in consistency under continuous control, both on synthetic and real data.
title PD$^{2}$GS: Part-Level Decoupling and Continuous Deformation of Articulated Objects via Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.09663