| Submission name | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Submission time (UTC) | Feb. 28, 2024, 11:41 a.m. | ||||||||||
| User | nvnguyen | ||||||||||
| Task | 6D localization of unseen objects | ||||||||||
| Dataset | ITODD | ||||||||||
| 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 | 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 |