yfeng95 / PRNet

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018)
http://openaccess.thecvf.com/content_ECCV_2018/papers/Yao_Feng_Joint_3D_Face_ECCV_2018_paper.pdf
MIT License
4.95k stars 947 forks source link

How does the 3DMM point semantically correspond with the given face_ind.txt? #92

Open OptimusPrimeCao opened 5 years ago

OptimusPrimeCao commented 5 years ago

In training time, the position map was processed using interpolation from 'float-type' uv-map in your https://github.com/YadiraF/face3d/blob/master/examples/8_generate_posmap_300WLP.py

However, in your demo.py, I see you use a face_ind.txt to allocate a position in position map to certain 3DMM sematic point. Where do I can get such correspondence? Thanks!