Model-based 6D detection of unseen objects – LM-O

This leaderbord shows the ranking for Model-based 6D detection of unseen objects on LM-O. The reported time is the average image processing time.

Date (UTC) Submission Test image AP APMSSD APMSPD Time (s)
2024-09-19 FreeZe.v2 (SAM6D) (SAR threshold = -1) RGB-D 0.775 0.759 0.791 80.277
2024-09-26 FreeZe.v2 (SAM6D, Coarse-to-Fine) (0.45 to 0.25) RGB-D 0.743 0.729 0.757 14.875
2024-09-17 FreeZe.v2 (SAM6D) RGB-D 0.719 0.705 0.733 8.766
2024-09-26 FreeZe.v2 (SAM6D, Coarse-to-Fine) RGB-D 0.694 0.682 0.705 14.842
2024-09-16 Co-op (SAM6D, Coarse, RGBD) (Coarse only, magsac++, det thres=0.4 / Intel(R) Core(TM) i9-14900K, RTX4090) RGB-D 0.684 0.667 0.702 0.832
2024-09-17 Co-op (CNOS, 5 Hypo, RGBD) (genflow rescoring(no meaning) / Intel(R) Core(TM) i9-14900K, RTX4090) RGB-D 0.657 0.640 0.675 33.332
2024-09-17 Co-op (SAM6D, 5 Hypo, RGBD) (genflow rescoring(no meaning) / Intel(R) Core(TM) i9-14900K, RTX4090) RGB-D 0.656 0.639 0.674 29.594
2024-09-28 Co-op (SAM6D, 5 Hypo) (genflow coarse score recalc / Intel(R) Core(TM) i9-14900K, RTX4090) RGB 0.612 0.548 0.675 26.499
2024-09-28 Co-op (CNOS, 5 Hypo) (genflow coarse score recalc / Intel(R) Core(TM) i9-14900K, RTX4090) RGB 0.606 0.544 0.669 29.971
2024-09-20 GigaPose+GenFlow (5 hypothesis) RGB 0.597 0.533 0.661 23.131
2024-09-13 GigaPose+GenFlow (1 hypothesis) (RGBD) (threshold = 0.0) RGB-D 0.578 0.561 0.595 6.685
2024-09-27 GigaPose+GenFlow (1 hypothesis) (threshold = 0.6) RGB 0.554 0.494 0.614 6.857
2024-09-15 Co-op (CNOS, Coarse) (Coarse only / Intel(R) Core(TM) i9-14900K, RTX4090) RGB 0.429 0.370 0.488 2.145
2024-09-18 GigaPose+GenFlow+kabsch (5 hypothesis) RGB-D 0.237 0.230 0.244 25.082
2024-09-18 GigaPose-CVPR24 RGB 0.062 0.022 0.101 1.085

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