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) |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPR46437.2021.00893 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 |
DocType | ISSN | Citations |
Conference | 1063-6919 | 0 |
PageRank | References | Authors |
0.34 | 0 | 12 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yu-Wei Chao | 1 | 241 | 9.87 |
Wei Yang | 2 | 0 | 0.34 |
Yu Xiang | 3 | 629 | 23.04 |
Pavlo O. Molchanov | 4 | 198 | 11.96 |
Ankur Handa | 5 | 479 | 26.11 |
Jonathan Tremblay | 6 | 73 | 10.97 |
Yashraj S. Narang | 7 | 0 | 0.34 |
Karl Van Wyk | 8 | 4 | 1.17 |
Umar Iqbal | 9 | 13 | 6.99 |
Stan Birchfield | 10 | 1406 | 193.73 |
Jan Kautz | 11 | 3615 | 198.77 |
Dieter Fox | 12 | 2427 | 249.17 |