Submitted to: BOP Challenge 2023

Training data: real + provided PBR

Used 3D models: Reconstructed for T-LESS, default for other datasets

Notes:

Authors: Ruida Zhang, Ziqin Huang, Gu Wang, Xingyu Liu, Chenyangguang Zhang and Xiangyang Ji. (Tsinghua University)

GDRNPP + coordinate-guided depth refinement, using default detection. A network is trained for each object.