| Submission name | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Submission time (UTC) | Feb. 28, 2024, 11:49 a.m. | ||||||||||
| User | nvnguyen | ||||||||||
| Task | 6D localization of unseen objects | ||||||||||
| Dataset | TUD-L | ||||||||||
| Description | |||||||||||
| Evaluation scores |
|
| 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 | We use GigaPose (Nguyen et al., CVPR 2024) to extract 5 coarse pose hypothesis, then refine the pose with MegaPose (Labbé et al., CoRL 2022). The final prediction is selected by coarse network of MegaPose. GigaPose: https://github.com/nv-nguyen/gigapose MegaPose: https://github.com/megapose6d/megapose6d |
| Computer specifications | V100 |