DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes

Jialiang Zhang, Haoran Liu, Danshi Li, XinQiang Yu, Haoran Geng, Yufei Ding, Jiayi Chen, He Wang
Proceedings of The 8th Conference on Robot Learning, PMLR 270:5106-5133, 2025.

Abstract

Grasping in cluttered scenes remains highly challenging for dexterous hands due to the scarcity of data. To address this problem, we present a large-scale synthetic dataset, encompassing 1319 objects, 8270 scenes, and 426 million grasps. Beyond benchmarking, we also explore data-efficient learning strategies from grasping data. We reveal that the combination of a conditional generative model that focuses on local geometry and a grasp dataset that emphasizes complex scene variations is key to achieving effective generalization. Our proposed generative method outperforms all baselines in simulation experiments. Furthermore, it demonstrates zero-shot sim-to-real transfer through test-time depth restoration, attaining 91% real-world success rate, showcasing the robust potential of utilizing fully synthetic training data.

Cite this Paper


BibTeX
@InProceedings{pmlr-v270-zhang25j, title = {DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes}, author = {Zhang, Jialiang and Liu, Haoran and Li, Danshi and Yu, XinQiang and Geng, Haoran and Ding, Yufei and Chen, Jiayi and Wang, He}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {5106--5133}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/zhang25j/zhang25j.pdf}, url = {https://proceedings.mlr.press/v270/zhang25j.html}, abstract = {Grasping in cluttered scenes remains highly challenging for dexterous hands due to the scarcity of data. To address this problem, we present a large-scale synthetic dataset, encompassing 1319 objects, 8270 scenes, and 426 million grasps. Beyond benchmarking, we also explore data-efficient learning strategies from grasping data. We reveal that the combination of a conditional generative model that focuses on local geometry and a grasp dataset that emphasizes complex scene variations is key to achieving effective generalization. Our proposed generative method outperforms all baselines in simulation experiments. Furthermore, it demonstrates zero-shot sim-to-real transfer through test-time depth restoration, attaining 91% real-world success rate, showcasing the robust potential of utilizing fully synthetic training data.} }
Endnote
%0 Conference Paper %T DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes %A Jialiang Zhang %A Haoran Liu %A Danshi Li %A XinQiang Yu %A Haoran Geng %A Yufei Ding %A Jiayi Chen %A He Wang %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-zhang25j %I PMLR %P 5106--5133 %U https://proceedings.mlr.press/v270/zhang25j.html %V 270 %X Grasping in cluttered scenes remains highly challenging for dexterous hands due to the scarcity of data. To address this problem, we present a large-scale synthetic dataset, encompassing 1319 objects, 8270 scenes, and 426 million grasps. Beyond benchmarking, we also explore data-efficient learning strategies from grasping data. We reveal that the combination of a conditional generative model that focuses on local geometry and a grasp dataset that emphasizes complex scene variations is key to achieving effective generalization. Our proposed generative method outperforms all baselines in simulation experiments. Furthermore, it demonstrates zero-shot sim-to-real transfer through test-time depth restoration, attaining 91% real-world success rate, showcasing the robust potential of utilizing fully synthetic training data.
APA
Zhang, J., Liu, H., Li, D., Yu, X., Geng, H., Ding, Y., Chen, J. & Wang, H.. (2025). DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:5106-5133 Available from https://proceedings.mlr.press/v270/zhang25j.html.

Related Material