Submission: GDRNPP-PBRReal-RGBD-MModel-OfficialDet/ITODD

Download submission
Submission name
Submission time (UTC) Oct. 13, 2022, 2:22 a.m.
User zyMeteroid
Task 6D localization of seen objects
Dataset ITODD
Training model type Default
Training image type Synthetic (only PBR images provided for BOP Challenge 2020 were used)
Description
Evaluation scores
AR:0.543
AR_MSPD:0.563
AR_MSSD:0.568
AR_VSD:0.498
average_time_per_image:5.891

Method: GDRNPP-PBRReal-RGBD-MModel-OfficialDet

User zyMeteroid
Publication Not yet
Implementation Pytorch, code can be found at https://github.com/shanice-l/gdrnpp_bop2022
Training image modalities RGB-D
Test image modalities RGB-D
Description

GDRNPP for BOP2022 with Official Detection

Authors: Xingyu Liu, Ruida Zhang, Chenyangguang Zhang, Bowen Fu, Jiwen Tang, Xiquan Liang, Jingyi Tang, Xiaotian Cheng, Yukang Zhang, Gu Wang, and Xiangyang Ji.

We test GDPNPP_PBRReal_RGB_MModel with official detection provided by bop2022. Then we utilize depth information to further refine the estimated pose. We adopt depth refinement inspired by Coupled Iterative Refinement.

Computer specifications GPU RTX 3090; CPU AMD EPYC 7H12 64-Core Processor.