BEDLAM is a large-scale synthetic video dataset designed to train and test algorithms on the task of 3D human pose and shape estimation (HPS). It contains diverse body shapes, skin tones, and motions. The clothing is realistically simulated on the moving bodies using commercial clothing physics simulation.
Variants: BEDLAM
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Human Mesh Recovery | Multi-HMR | Multi-HMR: Multi-Person Whole-Body Human Mesh … | 2024-02-22 |
| Human Mesh Recovery | BEDLAM-CLIFF+ | CLIFF: Carrying Location Information in … | 2022-08-01 |
| Human Mesh Recovery | BEDLAM-CLIFF | CLIFF: Carrying Location Information in … | 2022-08-01 |
Recent papers with results on this dataset: