6D localization of unseen objects – Core datasets

This leaderbord shows the overall ranking for Task 4 on the core datasets (LM-O, T-LESS, TUD-L, IC-BIN, ITODD, HB, YCB-V). For each method, the date of the latest considered submission is reported. If more submissions of a method are available for a dataset, the submission with the highest ARCore score is considered. The reported time is the average image processing time averaged over the core datasets.

Date (UTC) Method Test image ARCore ARLM-O ART-LESS ARTUD-L ARIC-BIN ARITODD ARHB ARYCB-V Time (s)
2023-08-22 ZeroPose-One-Hypo RGB-D 0.348 0.272 0.156 0.536 0.307 0.362 0.462 0.341 9.756
2023-09-20 ZeroPose-Multi-Hypo-Refinement RGB-D 0.534 0.493 0.342 0.790 0.396 0.465 0.629 0.623
2023-09-04 CNOS_fastSAM+MegaPose RGB 0.509 0.499 0.477 0.653 0.367 0.315 0.654 0.601 31.724
2023-09-04 CNOS_fastSAM+MegaPose MultiHyp RGB 0.534 0.529 0.498 0.687 0.385 0.339 0.684 0.616 35.477