Submission: Pix2Pose-Resnet-ICCV19/YCB-V

Submission name
Submission time (UTC) Nov. 28, 2019, 9:02 a.m.
User kirumang
Dataset YCB-V
Training model type Default
Training image type Real
Description Every setup is the same as performed for the BOP 2019.
Evaluation scores
bop19_average_recall:0.434
bop19_average_recall_mspd:0.564
bop19_average_recall_mssd:0.395
bop19_average_recall_vsd:0.343
bop19_average_time_per_image:1.034

Method: Pix2Pose-Resnet-ICCV19

User kirumang
Publication Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation, ICCV 2019
Implementation https://github.com/kirumang/Pix2Pose
Training image modalities RGB
Test image modalities RGB
Description Replaced the encoder part using pre-trained Resnet-50 (first three blocks). Other setups are the same as used in the BOP 2019 submissions.
Computer specifications CPU: i7-9700K, GPU: GTX 1070Ti, RAM: 32GB