Submission: SAM6D/HB
Download submission
| Submission name |
|
| Submission time (UTC) |
Dec. 5, 2023, 7:50 a.m.
|
| User |
jiehonglin
|
| Task |
Model-based 2D segmentation of unseen objects |
| Dataset |
HB |
| Description |
|
| Evaluation scores |
| AP: | 0.593 |
| AP50: | 0.759 |
| AP75: | 0.673 |
| AP_large: | 0.704 |
| AP_medium: | 0.605 |
| AP_small: | 0.004 |
| AR1: | 0.627 |
| AR10: | 0.639 |
| AR100: | 0.639 |
| AR_large: | 0.770 |
| AR_medium: | 0.643 |
| AR_small: | 0.041 |
| average_time_per_image: | 2.957 |
|
| User |
jiehonglin
|
| Publication |
SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation |
| Implementation |
https://github.com/JiehongLin/SAM-6D/ |
| Training image modalities |
RGB-D |
| Test image modalities |
RGB-D |
| Description |
|
| Computer specifications |
GeForce RTX 3090 24G； Inter (R) Xeon (R) CPU E5-2678 v3 @ 2.50Ghz |