| User | nvnguyen |
|---|---|
| Publication | https://arxiv.org/abs/2311.14155 |
| Implementation | https://github.com/nv-nguyen/gigapose |
| Training image modalities | RGB |
| Test image modalities | RGB |
| Description | GigaPose (Nguyen et al., CVPR 2024) is a "hybrid" template-patch correspondence approach to estimate 6D pose of novel objects in RGB images: GigaPose first uses 162 templates, rendered images of the CAD models, to recover the out-of-plane rotation (2DoF) and then uses patch correspondences to estimate the remaining 4DoF. |
| Computer specifications | V100 |
| Date | Submission name | Dataset | ||
|---|---|---|---|---|
| 2024-02-28 11:40 | - | LM-O | ||
| 2024-02-28 11:40 | - | T-LESS | ||
| 2024-02-28 11:41 | - | IC-BIN | ||
| 2024-02-28 11:41 | - | ITODD | ||
| 2024-02-28 11:42 | - | HB | ||
| 2024-02-28 11:42 | - | YCB-V | ||
| 2024-02-28 12:19 | - | TUD-L |