Submission: CosyPose-ECCV20-SYNT+REAL-1VIEW-ICP/YCB-V

Download submission
Submission name
Submission time (UTC) Aug. 18, 2020, 7:14 p.m.
User yann_labbe
Task Model-based 6D localization of seen objects
Dataset YCB-V
Training model type Default
Training image type Synthetic + real
Description
Evaluation scores
AR:0.861
AR_MSPD:0.849
AR_MSSD:0.903
AR_VSD:0.831
average_time_per_image:2.736

Method: CosyPose-ECCV20-SYNT+REAL-1VIEW-ICP

User yann_labbe
Publication Labbé et al, CosyPose: Consistent multi-view multi-object 6D pose estimation, ECCV 2020
Implementation https://github.com/ylabbe/cosypose
Training image modalities RGB
Test image modalities RGB-D
Description

We apply ICP to each individual 6D pose estimates. The pose estimates are the ones from CosyPose-ECCV20-SYNT+REAL-1VIEW. We use parts of Pix2pose's ICP implementation https://github.com/kirumang/Pix2Pose/blob/master/tools/5_evaluation_bop_icp3d.py.

MaskRCNN predicted masks are used to pick the 3D points that correspond to the detection in the depth.

Computer specifications CPU: 20-core Intel Xeon 6164 @ 3.2 GHz, GPU: Nvidia V100