DexYCB: A Benchmark for Capturing Hand Grasping of Objects
Yu-Wei Chao, Wei Yang, Yu Xiang, Pavlo Molchanov, Ankur Handa, Jonathan Tremblay, Yashraj Narang, Karl Van Wyk, Umar Iqbal, Stan Birchfield, Jan Kautz, Dieter Fox
2021Year
138Top-tier citations
Abstract
We introduce DexYCB, a new dataset for capturing hand grasping of objects. We first compare DexYCB with a related one through cross-dataset evaluation. We then present a thorough benchmark of state-of-the-art approaches on three relevant tasks: 2D object and keypoint detection, 6D object pose estimation, and 3D hand pose estimation. Finally, we evaluate a new robotics-relevant task: generating safe robot grasps in human-to-robot object handover.1
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.
Cited by top-tier papers138
- EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric VideoRyan Hoque, Peide Huang, David J. Yoon, Mouli Sivapurapu et al.ICLR 2026 · 248 citations
- HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object InteractionYunze Liu, Yun Liu, Che Jiang, Kangbo Lyu et al.CVPR 2022 · 126 citations
- P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel PromptingZiyi Wang, Xumin Yu, Yongming Rao, Jie Zhou et al.NeurIPS 2022 · 121 citations
- HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation NetworkJoonKyu Park, Yeonguk Oh, Gyeongsik Moon, Hongsuk Choi et al.CVPR 2022 · 116 citations
- Reconstructing Hands in 3D with TransformersGeorgios Pavlakos, Dandan Shan, Ilija Radosavovic, Angjoo Kanazawa et al.CVPR 2024 · 110 citations
Builds on9
- Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose EstimationKiru Park, Timothy Patten, Markus VinczeICCV 2019 · 527 citations
- FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape From Single RGB ImagesChristian Zimmermann, Duygu Ceylan, Jimei Yang, Bryan C. Russell et al.ICCV 2019 · 493 citations
- A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation From a Single Depth ImageFu Xiong, Boshen Zhang, Yang Xiao, Zhiguo Cao et al.ICCV 2019 · 178 citations
- Understanding Human Hands in Contact at Internet ScaleDandan Shan, Jiaqi Geng, Michelle Shu, David F. FouheyCVPR 2020
- Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object ReconstructionYana Hasson, Bugra Tekin, Federica Bogo, Ivan Laptev et al.CVPR 2020
Related papers
- DexH2R: A Benchmark for Dynamic Dexterous Grasping in Human-To-Robot HandoverYouzhuo Wang, Jiayi Ye, Chuyang Xiao, Yiming Zhong et al.ICCV 2025 · 1 citation
- DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics AwarenessYiming Zhong, Qi Jiang, Jingyi Yu, Yuexin MaCVPR 2025
- GraspNet-1Billion: A Large-Scale Benchmark for General Object GraspingHaoshu Fang, Chenxi Wang, Minghao Gou, Cewu LuCVPR 2020
- H2O: A Benchmark for Visual Human-human Object Handover AnalysisRuolin Ye, Wenqiang Xu, Zhendong Xue, Tutian Tang et al.ICCV 2021 · 30 citations
- GanHand: Predicting Human Grasp Affordances in Multi-Object ScenesEnric Corona, Albert Pumarola, Guillem Alenyà, Francesc Moreno-Noguer et al.CVPR 2020
