|Submission time (UTC)||Oct. 14, 2022, 12:13 p.m.|
|Task||2D detection of seen objects|
|Training model type||None|
|Training image type||Synthetic (only PBR images provided for BOP Challenge 2020 were used)|
|Implementation||Pytorch, code can be found at https://github.com/shanice-l/gdrnpp_bop2022|
|Training image modalities||RGB|
|Test image modalities||RGB|
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).
In the PBR setting, all models are trained only using the provided PBR synthetic data. We trained one model for each dataset.
GDRNPPDet was based on YOLOX. We used stronger data augmentation and ranger optimizer.
|Computer specifications||GPU RTX 3090; CPU AMD EPYC 7H12 64-Core Processor.|