zhangchenxu528 / FACIAL

FACIAL: Synthesizing Dynamic Talking Face With Implicit Attribute Learning. ICCV, 2021.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

render_netface_fitpose produces cropped rendered images

NicoSperry opened this issue · comments

Hi,

I've generated the face model .mat files using Deep3DFaceRecon_pytorch, and the facial features using OpenFace, however the resulting rendered images used for training are cropped heavily. I am not sure if it is an issue with render_netface_fitpose.py or fit_headpose.py, or if the Deep3DFaceRecon_pytorch .mat files are still incorrect (I modified handle_netface.py as mentioned in #26, as the pytorch version uses different keys). I have attached an example output and the corresponding true image. Thank you very much for your help.

000001
0001

In your result, the head poses translation may not be correct. I guess fit_headpose.py didn't work here.