|Publication||Labbé et al.: MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare, CoRL 2022|
|Training image modalities||RGB|
|Test image modalities||RGB|
This submission was prepared by Mederic Fourmy, Elliot Maître, Lucas Manuelli, Yann Labbé
In this submission, GDRNPPDet_PBRReal, [A] detections (default detections for Task 1) are used as input to the MegaPose pose estimation method [B], without fine tuning on the core BOP challenge datasets.
For each detection, we run the MegaPose coarse network and refine the 1-best coarse estimate with 5 refiner iterations.
The following improvement has been made over the original MegaPose paper [B]:
Instructions to reproduce these results will be made available on https://github.com/agimus-project/happypose.
[A] Liu et al.: https://github.com/shanice-l/gdrnpp_bop2022
This work was granted access to the HPC resources of IDRIS under the allocation 011014301 made by GENCI
|Computer specifications||NVIDIA Tesla V100 32Go|