DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects
Chen Bao, Helin Xu, Yuzhe Qin, Xiaolong Wang
2023Year
16Top-tier citations
Abstract
(a) DexArt Task Suite (b) Seen Objects (c) Unseen Objects Figure 1. Overview. (a) We propose DexArt, a task suite of Dexterous manipulation with Articulated object using point cloud observation. (b) We experiment with extensive benchmark methods that learn category-level manipulation policy on seen objects. (c) We evaluate the policies' generalizability on a collection of unseen objects, as well as their robustness to camera viewpoint change.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext a1944f64-537d-42d2-9592-63ed1e2340beCited by top-tier papers16
- DexMachina: Functional Retargeting for Bimanual Dexterous ManipulationZhao Mandi, Yifan Hou, Dieter Fox, Yashraj Narang et al.ICML 2026 · 55 citations
- VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action ModelsChongkai Gao, Zixuan Liu, Zhenghao Chi, Junshan Huang et al.NeurIPS 2025 · 41 citations
- Dense Policy: Bidirectional Autoregressive Learning of ActionsYue Su, Xinyu Zhan, Hongjie Fang, Han Xue et al.ICCV 2025 · 23 citations
- DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable PolicyYuran Wang, Ruihai Wu, Yue Chen, Jiarui Wang et al.NeurIPS 2025 · 22 citations
- FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency ConsistencyYifei Su, Ning Liu, Dong Chen, Zhen Zhao et al.NeurIPS 2025 · 20 citations
Builds on13
- Unsupervised Point Cloud Pre-training via Occlusion CompletionHanchen Wang, Qi Liu, Xiangyu Yue, Joan Lasenby et al.ICCV 2021 · 323 citations
- Where2Act: From Pixels to Actions for Articulated 3D ObjectsKaichun Mo, Leonidas J. Guibas, Mustafa Mukadam, Abhinav Gupta et al.ICCV 2021 · 240 citations
- A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape RepresentationJiteng Mu, Weichao Qiu, Adam Kortylewski, Alan L. Yuille et al.ICCV 2021 · 138 citations
- VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated ObjectsRuihai Wu, Yan Zhao, Kaichun Mo, Zizheng Guo et al.ICLR 2022 · 119 citations
- CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point CloudsYijia Weng, He Wang, Qiang Zhou, Yuzhe Qin et al.ICCV 2021 · 119 citations
Related papers
- UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned PolicyYinzhen Xu, Weikang Wan, Jialiang Zhang, Haoran Liu et al.CVPR 2023
- UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist LearningWeikang Wan, Haoran Geng, Yun Liu, Zikang Shan et al.ICCV 2023 · 160 citations
- Benchmarking Offline Reinforcement Learning on Real-Robot HardwareNico Gürtler, Sebastian Blaes, Pavel Kolev, Felix Widmaier et al.ICLR 2023 · 11 citations
- AdaManip: Adaptive Articulated Object Manipulation Environments and Policy LearningYuanfei Wang, Xiaojie Zhang, Ruihai Wu, Yu Li et al.ICLR 2025
- Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous GraspingZiye Huang, Haoqi Yuan, Yuhui Fu, Zongqing LuICLR 2025
