Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.22666 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911544949866496 |
|---|---|
| author | Li, Xuelu Wang, Zhaonan Wang, Xiaogang Wu, Lei Li, Manyi Tu, Changhe |
| author_facet | Li, Xuelu Wang, Zhaonan Wang, Xiaogang Wu, Lei Li, Manyi Tu, Changhe |
| contents | Reconstructing articulated objects into high-fidelity digital twins is crucial for applications such as robotic manipulation and interactive simulation. Recent self-supervised methods using differentiable rendering frameworks like 3D Gaussian Splatting remain highly sensitive to the initial part segmentation. Their reliance on heuristic clustering or pre-trained models often causes optimization to converge to local minima, especially for complex multi-part objects. To address these limitations, we propose ArtPro, a novel self-supervised framework that introduces adaptive integration of mobility proposals. Our approach begins with an over-segmentation initialization guided by geometry features and motion priors, generating part proposals with plausible motion hypotheses. During optimization, we dynamically merge these proposals by analyzing motion consistency among spatial neighbors, while a collision-aware motion pruning mechanism prevents erroneous kinematic estimation. Extensive experiments on both synthetic and real-world objects demonstrate that ArtPro achieves robust reconstruction of complex multi-part objects, significantly outperforming existing methods in accuracy and stability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22666 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposals Li, Xuelu Wang, Zhaonan Wang, Xiaogang Wu, Lei Li, Manyi Tu, Changhe Computer Vision and Pattern Recognition Reconstructing articulated objects into high-fidelity digital twins is crucial for applications such as robotic manipulation and interactive simulation. Recent self-supervised methods using differentiable rendering frameworks like 3D Gaussian Splatting remain highly sensitive to the initial part segmentation. Their reliance on heuristic clustering or pre-trained models often causes optimization to converge to local minima, especially for complex multi-part objects. To address these limitations, we propose ArtPro, a novel self-supervised framework that introduces adaptive integration of mobility proposals. Our approach begins with an over-segmentation initialization guided by geometry features and motion priors, generating part proposals with plausible motion hypotheses. During optimization, we dynamically merge these proposals by analyzing motion consistency among spatial neighbors, while a collision-aware motion pruning mechanism prevents erroneous kinematic estimation. Extensive experiments on both synthetic and real-world objects demonstrate that ArtPro achieves robust reconstruction of complex multi-part objects, significantly outperforming existing methods in accuracy and stability. |
| title | ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposals |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.22666 |