Submission: GDRNPPDet_PBRReal/TUD-L

Download submission
Submission name
Submission time (UTC) Oct. 14, 2022, 12:28 p.m.
User zyMeteroid
Task Model-based 2D detection of seen objects
Dataset TUD-L
Training model type None
Training image type Synthetic + real
Description
Evaluation scores
AP:0.895
AP50:1.000
AP75:0.993
AP_large:0.923
AP_medium:0.898
AP_small:0.826
AR1:0.914
AR10:0.914
AR100:0.914
AR_large:0.952
AR_medium:0.909
AR_small:0.825
average_time_per_image:0.078

Method: GDRNPPDet_PBRReal

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

GDRNPPDet for BOP2022

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 PBRReal setting, for LMO, HB, ICBIN and ITODD datasets, we only use the provided synthetic training data (PBR) in training. While for YCBV, TUDL, TLESS, we use the provided real data and synthetic data (PBR) in training. 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.