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

2026-02-26

AI Summary

This work proposes a self-supervised, annotation-free framework for reconstructing articulated objects that overcomes the sensitivity of existing methods to initial part segmentation and their tendency to converge to suboptimal solutions, especially in complex multi-part structures. The approach begins by generating an over-segmented set of motion hypotheses using geometric and motion priors. During optimization, it dynamically merges spatially adjacent parts with consistent motion and incorporates a collision-aware mechanism to eliminate implausible motion estimates. By integrating differentiable 3D Gaussian splatting rendering, geometry-guided over-segmentation, and an adaptive motion-proposal fusion strategy, the method significantly reduces reliance on accurate initial segmentation. Experiments on both synthetic and real-world datasets demonstrate superior reconstruction accuracy and stability compared to current state-of-the-art approaches.

Technology Category

• Computer Vision: Motion & Tracking
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• articulated object reconstruction
• self-supervised learning
• initial segmentation sensitivity
• local minima
• multi-part objects

Innovation

• self-supervised reconstruction
• articulated objects
• adaptive integration
• motion consistency
• collision-aware pruning