DexYCB is a dataset for capturing hand grasping of objects. It can be used three relevant tasks: 2D object and keypoint detection, 6D object pose estimation, and 3D hand pose estimation.
The dataset was built using 20 objects from the YCB-Video dataset, and consists of multiple trials from 10 subjects. For each trial, there is a target object with 2 to 4 other objects placed on a table. The subject is asked to start from a relaxed pose, pick up the target object, and hold it in the air. Some subjects were asked to pretend to hand over the object to someone across from them. Each action is recorded for 3 seconds, repeating the trial 5 times for each target object, each time with a random set of accompanied objects and placement. In total there are 100 trials per subject, and 1,000 trials in total for all subjects.
Source: DexYCB: A Benchmark for Capturing Hand Grasping of Objects
Variants: DexYCB
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| 3D Hand Pose Estimation | MaskHand | MMHMR: Generative Masked Modeling for … | 2024-12-18 |
| 3D Hand Pose Estimation | SimpleHand | A Simple Baseline for Efficient … | 2024-03-04 |
| 3D Hand Pose Estimation | SemGCN | 3D Hand Reconstruction via Aggregating … | 2024-03-04 |
| 3D Hand Pose Estimation | HOISDF | HOISDF: Constraining 3D Hand-Object Pose … | 2024-02-26 |
| 3D Hand Pose Estimation | HandOccNet | HandOccNet: Occlusion-Robust 3D Hand Mesh … | 2022-03-28 |
| 3D Hand Pose Estimation | MobRecon | MobRecon: Mobile-Friendly Hand Mesh Reconstruction … | 2021-12-06 |
| 3D Hand Pose Estimation | SHO | Semi-Supervised 3D Hand-Object Poses Estimation … | 2021-06-09 |
| 3D Hand Pose Estimation | METRO | End-to-End Human Pose and Mesh … | 2020-12-17 |
| 3D Hand Pose Estimation | BMC | Weakly Supervised 3D Hand Pose … | 2020-03-20 |
Recent papers with results on this dataset: