hillaric
hillaric
In fact, you use uv_map to calculate the photo_detail loss rather than the image, which is different with the paper, could you give some reasons.
Where is the code of hitnet? I don't understand
the google drive and docker method do not work!
thank you! I will have a try.
The 'blender K' in common.py is the same K used in the 'occ_linemod'? I am a little confused.
Would you mind provide the corresponding code, especially the gt.yml. I try, but I can't do it. 
After using the code 'Pose_transformer' you released in 'base_utils.py' for OCCLUSION_LINEMOD, I got a different pose from PVNet. Is it right?
yes, I got the same result, but I still have the same error.
I meet the same question, do you have a solution?
Can you show the result for two images, I also align the testing data, but nothing change. You should have a try, which is more effective than your word.