| Submission name | CosyPose-LS | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Submission time (UTC) | Feb. 26, 2022, 8:36 p.m. | ||||||||||
| User | swtyree | ||||||||||
| Task | Model-based 6D localization of seen objects | ||||||||||
| Dataset | HOPE | ||||||||||
| Training model type | Default | ||||||||||
| Training image type | Synthetic (custom) | ||||||||||
| Description | |||||||||||
| Evaluation scores |
|
| User | swtyree |
|---|---|
| Publication | Labbé et al., "CosyPose: Consistent multi-view multi-object 6D pose estimation", ECCV, 2020. |
| Implementation | https://github.com/ylabbe/cosypose |
| Training image modalities | RGB |
| Test image modalities | RGB-D |
| Description | CosyPose + BlenderProc synthetic training images, with simple line-search for alignment to RGB-D. |
| Computer specifications |