Model-based 6D detection of unseen objects – HANDAL

This leaderbord shows the ranking for Model-based 6D detection of unseen objects on HANDAL. The reported time is the average time to generate predictions for all objects in a single image (averaged over the datasets).

Date (UTC) Submission Views Test image AP APMSSD APMSPD Time (s)
2025-11-14 3PT-Pose (Nov 2025) Multi RGB 0.657 0.595 0.718 14.522
2025-10-01 3PT-Pose-H3 (f.k.a IPT) Single RGB-D 0.646 0.569 0.724 38.142
2025-10-01 Co-op (MUSE, 1 Hypo) Single RGB 0.477 0.450 0.504 3.237
2025-09-18 Co-op (CNOS, 1 Hypo) Single RGB 0.454 0.432 0.476 4.780
2025-09-17 Co-op (CNOS, Coarse) (Inlier ratio) Single RGB 0.393 0.348 0.438 2.407
2024-11-20 OPFormer (CNOS, Megapose Refiner) Single RGB 0.262 0.230 0.294 2.334
2024-09-24 GigaPose + GenFlow (threshold = 0.6) Single RGB 0.256 0.239 0.273 4.355
2024-09-23 GigaPose + GenFlow Single RGB 0.193 0.174 0.213 4.065
2024-11-20 OPFormer (CNOS) Single RGB 0.192 0.134 0.250 0.477
2024-09-23 GigaPose-CVPR24 single RGB 0.041 0.018 0.065 0.818

Tip: Hover over the numbers to see more decimal places.

Latest submissions to this leaderboard: