Submission: SC6D/YCB-V/monocular-RGB + PBR+REAL

Submission name monocular-RGB + PBR+REAL
Submission time (UTC) June 10, 2022, 8:08 a.m.
User caidingd
Task Pose estimation (BOP 2019-2022)
Dataset YCB-V
Training model type None
Training image type Synthetic + real
Description The paper (can be found at https://arxiv.org/abs/2208.02129) is accepted by 3DV 2022.
Evaluation scores
AR:0.765
AR_MSPD:0.804
AR_MSSD:0.796
AR_VSD:0.695
average_time_per_image:0.351

Method: SC6D

User caidingd
Publication SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimation, 3DV, 2022
Implementation Implementation code at https://github.com/dingdingcai/SC6D-pose
Training image modalities RGB
Test image modalities RGB
Description

The default object detection results (provided by CosyPose) from BOP Challenge 2022 are used for evaluation, and the paper can be found at https://arxiv.org/abs/2208.02129

Computer specifications AMD 835 Ryzen 3970X CPU + an NVIDIA RTX3090 GPU