Submission: FoundationPose(NVIDIA)/TUD-L
Download submission
| Submission name |
|
| Submission time (UTC) |
Aug. 27, 2024, 6:47 a.m.
|
| User |
sadpose
|
| Task |
Model-based 6D localization of unseen objects |
| Dataset |
TUD-L |
| Description |
SAM6D mask
|
| Evaluation scores |
| AR: | 0.923 |
| AR_MSPD: | 0.964 |
| AR_MSSD: | 0.966 |
| AR_VSD: | 0.839 |
| average_time_per_image: | 17.714 |
|
| User |
sadpose
|
| Publication |
Wen et al: FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects, CVPR 2024 |
| Implementation |
https://github.com/NVlabs/FoundationPose |
| Training image modalities |
RGB-D |
| Test image modalities |
RGB-D |
| Description |
SAM6D mask
|
| Computer specifications |
GPU A100 |