search

THU-DA-6D-Pose-Group / GDR-Net

GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation. (CVPR 2021)
https://github.com/THU-DA-6D-Pose-Group/GDR-Net
Apache License 2.0
277 stars 47 forks source link

LM-O Training Split Question #82

Closed aja9675 closed 2 years ago

aja9675 commented 2 years ago

When you train for LM-O, do you still use 15% of the LINEMOD data? Or do you use 100% of LINEMOD data?

wangg12 commented 2 years ago

We follow the setting in PoseCNN and DeepIM to use all LM real data for training on LM-O.

aja9675 commented 2 years ago

Thanks for clarifying!