Submission: GDRNPP-PBRReal-RGBD-MModel/HB

Download submission
Submission name
Submission time (UTC) Oct. 14, 2022, 6:59 a.m.
User zyMeteroid
Task 6D localization of seen objects
Dataset HB
Training model type Default
Training image type Synthetic (only PBR images provided for BOP Challenge 2020 were used)
Description
Evaluation scores
AR:0.926
AR_MSPD:0.952
AR_MSSD:0.942
AR_VSD:0.885
average_time_per_image:8.000

Method: GDRNPP-PBRReal-RGBD-MModel

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 BOP 2022

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

Based on GDPNPP_PBRReal_RGB_MModel, 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.