# Since triangle mesh is the most popular representation of 3D face, 
# the main part is mesh processing.
mesh/             # written in python and c++
|  cython/               # c++ files, use cython to compile 
|  io.py                 # read & write obj
|  vis.py                # plot mesh
|  transform.py          # transform mesh & estimate matrix
|  light.py              # add light & estimate light(to do)
|  render.py             # obj to image using rasterization render

mesh_numpy/      # the same with mesh/, with each part written in numpy
                 # slow but easy to learn and modify

# 3DMM is one of the most popular methods to generate & reconstruct 3D face.
morphable_model/
|  morphable_model.py    # morphable model class: generate & fit
|  fit.py                # estimate shape&expression parameters. 3dmm fitting.
|  load.py               # load 3dmm data

cd ./examples

• 3dmm. python 2_3dmm.py

  left: random example generated by 3dmm

  right: fitting face with 3dmm using 68 key points

  

• transform. python 3_transform.py
  left:

  fix camera position & use orthographic projection. (often used in reconstruction)

  then transform face object: scale, change pitch angle, change yaw angle, change roll angle

  right:

  fix obj position & use perspective projection(fovy=30). (simulating real views)

  then move camera position and rotate camera: from far to near, down & up, left & right, rotate camera

  

• light. python 4_light.py

  single point light: from left to right, from up to down, from near to far

  

• image map python 6_image_map.py

  render different attributes in image pixels.

  : depth, pncc, uv coordinates

  

• uv map python 7_uv_map.py

  render different attributes in uv coordinates.

  : colors(texture map), position(2d facial image & corresponding position map)

  

• Python 2 or Python 3

• Python packages:

  • numpy
  • skimage (for reading&writing image)
  • scipy (for loading mat)
  • matplotlib (for show)
  • Cython (for compiling c++ file)

1. Clone the repository

   git clone https://github.com/YadiraF/face3d
   cd face3d

2. Compile c++ files to .so for python use (ignore if you use numpy version)

   cd face3d/mesh/cython
   python setup.py build_ext -i 

3. Prepare BFM Data (ignore if you don't use 3dmm)

   see Data/BFM/readme.md

4. Run examples

   (examples use cython version, you can change mesh into mesh_numpy to use numpy version)

   cd examples
   python 1_pipeline.py 

   For beginners who want to continue researches on 3D faces, I strongly recommend you first run examples according to the order, then view the codes in mesh_numpy and read the comments written in the beginning in each file. Hope this helps!

   Moreover, I am new in computer graphics, so it would be great appreciated if you could point out some of my wrong expressions. Thanks!

• 2018/10/08 change structure. add comments. add introduction. add paper collections.
• 2018/07/15 first release