Is the GT pose of real_val accurate enough?

Question

Is the GT pose of real_val accurate enough?

Opened this issue 4 years ago · 2 comments

Hi, You mentioned in the readme "the ground truth of real training data generated by this method is not good enough." Is the GT pose in real_val accurate? When I run the NOCS detection code, the GT pose visualization image will be generated as shown below. It seems that the GT pose is not accurate. Have you encountered this problem?

Answer 1 · 2020-08-17T03:31:26.000Z

I encountered this also.That's why we generate the labels by ourselves, but we have to be consistent with the NOCS on val dataset to fairly compare with them.

Answer 2 · 2020-08-17T07:01:09.000Z

Have you reproduced a more accurate GT pose of val_dateset? If yes, can you share it with me?