search

matansel / pix2vertex

Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation
257 stars 38 forks source link

Porting to Octave? Improve python code? #15

Open MarlNox opened 3 years ago

MarlNox commented 3 years ago

Hello all,

I've been experimenting with your code in pytorch, and it is my understanding that there is a final step that is not applied using the python/torch method you've published. The results in this repo seem to be way more accurate than pytorch is able to provide. In that light I have two questions:

  1. Is this code runnable using Octave? or alternatively:
  2. Taking into account the Matlab version produces much better results. What is the difference between this code and and the pytorch one, does it change any steps for to account for the increase accuracy and result quality, or it misses any final step completely? If yes, which ones, so that I can promptly check that out.

Thank you,

eladrich commented 3 years ago

Hi, The new code includes only the depth reconstruction network, without the non-rigid ICP and the shape from shading steps, Please see the readme of the new repo for more. Currently, we have no plans to export these steps to octave or python.