
GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts
Haoran Geng*, Helin Xu*, Chengyang Zhao*, Chao Xu, Li Yi, Siyuan Huang, He Wang
CVPR 2023 Highlight (10% of accepted, scores: 5, 5, 5)
[Paper] [Project]
We propose to learn cross-category object perception and manipulation skills via Generalizable and Actionable Parts (GAParts). By identifying 9 GAPart classes (lids, handles, etc.) in 27 object categories, we construct GAPartNet, where we provide rich, part-level annotations (semantics, poses) for 8,489 part instances on 1,166 objects.