This leaderbord shows the ranking for Model-based 2D detection of unseen objects on HOPEv2. The reported time is the average time to generate predictions for all objects in a single image (averaged over the datasets).
| Date (UTC) | Submission | Test image | AP | AP50 | AP75 | APS | APM | APL | AR1 | AR10 | AR100 | ARS | ARM | ARL | Time (s) | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2025-11-14 | 3PT-Detection (Nov 2025) | RGB | 0.624 | 0.773 | 0.725 | 0.100 | 0.230 | 0.694 | 0.608 | 0.698 | 0.698 | 0.100 | 0.267 | 0.772 | 4.536 | |
| 2025-10-01 | 3PT-Detection (f.k.a IPT) | RGB | 0.618 | 0.763 | 0.716 | 0.100 | 0.217 | 0.689 | 0.603 | 0.683 | 0.683 | 0.100 | 0.240 | 0.761 | 40.402 | |
| 2025-08-26 | MUSE (muse_full) | RGB | 0.460 | 0.636 | 0.504 | 0.111 | 0.107 | 0.533 | 0.471 | 0.528 | 0.528 | 0.111 | 0.142 | 0.607 | 0.995 | |
| 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.