Closed kampelmuehler closed 2 years ago
Am I geussing correctly that you are uniformly scaling and translating ground truth meshes such that they fit within a box of [-0.5, 0.5]? Is it the same as here: https://github.com/jchibane/ndf/blob/master/dataprocessing/convert_to_scaled_off.py?
How do you take care of scaling back up (and potentially translating) at test time?
Hi,
Yes, the ground truth meshes are normalized to [-0.5, 0.5] which is the same as "convert_to_scaled_off.py" from ndf.
For testing, you can refer to compute_errors.py.
Am I geussing correctly that you are uniformly scaling and translating ground truth meshes such that they fit within a box of [-0.5, 0.5]? Is it the same as here: https://github.com/jchibane/ndf/blob/master/dataprocessing/convert_to_scaled_off.py?
How do you take care of scaling back up (and potentially translating) at test time?