search

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

The meaning of the position map ? #198

Open rakacendekia opened 3 years ago

rakacendekia commented 3 years ago

I would like to ask, what do the colors on the position map mean and how do they affect the face reconstruction process? Does it mean the same as in PNCC? IBUG_image_008_1_0_posmap

Suvi-dha commented 2 years ago

Yes, its same as pncc that is converting normalized x,y,z values to r,g,b values. The difference is that here x, y, z coordinates in 3d space is mapped to texture coordinates (vt_x, vt_y) associated with 3d model and then this map is plotted where x, y, z values are mapped to r,g,b values at locations vt_x, vt_y. Hope this made sense.