Submission: PFA-cosypose/ITODD/1view

Download submission
Submission name 1view
Submission time (UTC) July 28, 2022, 3:24 a.m.
User Yang-hai
Task Model-based 6D localization of seen objects
Dataset ITODD
Training model type Default
Training image type Synthetic (only PBR images provided for BOP Challenge 2020 were used)
Description
Evaluation scores
AR:0.246
AR_MSPD:0.330
AR_MSSD:0.208
AR_VSD:0.201
average_time_per_image:-1.000

Method: PFA-cosypose

User Yang-hai
Publication Yinlin Hu, et al, Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation, ECCV-2022
Implementation
Training image modalities RGB
Test image modalities RGB
Description

For this method, we use the available cosypose initial pose.

Computer specifications GPU:NVIDIA-3090