Submission: FCOS-CDPN-PBR/T-LESS

Download submission
Submission name
Submission time (UTC) July 23, 2022, 10:50 a.m.
User Yang-hai
Task 2D detection of seen objects
Dataset T-LESS
Training model type None
Training image type Synthetic (only PBR images provided for BOP Challenge 2020 were used)
Description
Evaluation scores
AP:0.625
AP50:0.760
AP75:0.676
AP_large:0.711
AP_medium:0.531
AP_small:0.022
AR1:0.648
AR10:0.774
AR100:0.775
AR_large:0.875
AR_medium:0.683
AR_small:0.114
average_time_per_image:0.052

Method: FCOS-CDPN-PBR

User Yang-hai
Publication CVPR-2019
Implementation https://github.com/LZGMatrix/BOP19_CDPN_2019ICCV/tree/bop2020
Training image modalities RGB
Test image modalities RGB
Description

As CDPN provides the trained detectors(FCOS+VoVNet 57) used in the 2020 6D Pose challenge, we test them to provide more comprehensive results for the detection track.

Computer specifications NVIDIA 3090