ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposals

TL;DR

ArtPro is a self-supervised framework for reconstructing articulated objects into high-fidelity digital models, using adaptive mobility proposals to improve robustness and accuracy over existing methods.

Contribution

It introduces adaptive integration of mobility proposals with dynamic merging and collision-aware pruning, enhancing reconstruction of complex multi-part objects.

Findings

Outperforms existing methods in accuracy and stability

Robust reconstruction of complex multi-part objects

Effective handling of motion proposals through adaptive merging

Abstract

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.