This leaderbord shows the ranking for Model-based 2D detection of unseen objects on HOPEv2. The metrics are defined in Section 2 of the BOP 2022 paper. The reported time is the average image processing time.
| Date (UTC) | Submission | Test image | AP | AP50 | AP75 | APS | APM | APL | AR1 | AR10 | AR100 | ARS | ARM | ARL | Time (s) | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2024-11-17 | MUSE (full) | RGB | 0.474 | 0.652 | 0.519 | 0.100 | 0.109 | 0.547 | 0.488 | 0.554 | 0.554 | 0.100 | 0.138 | 0.637 | 1.536 | |
| 2024-09-10 | CNOS (SAM) (Pyrender) | RGB | 0.365 | 0.590 | 0.388 | 0.089 | 0.072 | 0.419 | 0.406 | 0.453 | 0.453 | 0.089 | 0.101 | 0.521 | 2.345 | |
| 2024-09-19 | CNOS (FastSAM) (Pyrender) | RGB | 0.313 | 0.502 | 0.320 | 0.089 | 0.040 | 0.361 | 0.368 | 0.430 | 0.430 | 0.089 | 0.092 | 0.491 | 0.421 |
Tip: Hover over the numbers to see more decimal places.