search

suyz526 / ZebraPose

The implementation of the paper 'ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation' (CVPR2022)
MIT License
122 stars 20 forks source link

Asking for training details #33

Open wujun-cse opened 11 months ago

wujun-cse commented 11 months ago

Hi,

Thanks for your great job and your kindness in sharing your pretrained models!

I'm wondering if you could share the training details of other datasets in BOP besides YCBV and LM/LMO. Such as the choice of training data, the augmentation skills, etc.

It would be really helpful for reproducing your results and develop your method.

suyz526 commented 11 months ago

Hello,

Thanks for your interest in our work.

All config files are available in https://github.com/suyz526/ZebraPose/tree/main/zebrapose/config/config_BOP_effnet.

Please let me know if there is any problem with the config files.

wujun-cse commented 11 months ago

Hello,

Thanks for your interest in our work.

All config files are available in https://github.com/suyz526/ZebraPose/tree/main/zebrapose/config/config_BOP_effnet.

Please let me know if there is any problem with the config files.

Thanks! I will check it out.

wujun-cse commented 11 months ago

Hello,

Thanks for your interest in our work.

All config files are available in https://github.com/suyz526/ZebraPose/tree/main/zebrapose/config/config_BOP_effnet.

Please let me know if there is any problem with the config files.

The configurations are very useful and helpful. But I still have one question about the test dataset you use for HomebrewedDB. As BOP doesn't provide the ground truth for the test datasets, how do you conduct evaluation on the dataset for submitting to BOP?