GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation

TL;DR

This paper introduces a large-scale, part-centric dataset for articulated object manipulation that enhances depth perception and interaction pose prediction, enabling more robust and generalizable manipulation in household scenarios.

Contribution

The paper presents a novel dataset with detailed part annotations and a modular framework that improves manipulation performance over existing methods.

Findings

Dataset significantly improves depth estimation accuracy.

Enhanced interaction pose prediction in simulation and real-world.

Framework achieves superior robustness and generalization.

Abstract

Effectively manipulating articulated objects in household scenarios is a crucial step toward achieving general embodied artificial intelligence. Mainstream research in 3D vision has primarily focused on manipulation through depth perception and pose detection. However, in real-world environments, these methods often face challenges due to imperfect depth perception, such as with transparent lids and reflective handles. Moreover, they generally lack the diversity in part-based interactions required for flexible and adaptable manipulation. To address these challenges, we introduced a large-scale part-centric dataset for articulated object manipulation that features both photo-realistic material randomization and detailed annotations of part-oriented, scene-level actionable interaction poses. We evaluated the effectiveness of our dataset by integrating it with several state-of-the-art methods for depth estimation and interaction pose prediction. Additionally, we proposed a novel modular framework that delivers superior and robust performance for generalizable articulated object manipulation. Our extensive experiments demonstrate that our dataset significantly improves the performance of depth perception and actionable interaction pose prediction in both simulation and real-world scenarios. More information and demos can be found at: https://pku-epic.github.io/GAPartManip/.