Inference
/
3D-Machine-Learning
mirror of https://github.com/Xianpeng919/3D-Machine-Learning.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

add FLAME model

master
tbolkart 2020-02-05 10:38:52 +01:00
parent 1e603881ba
commit 7dbd47198c
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -431,6 +431,11 @@ _Parametric Morphable Model-based methods_
<b>A Morphable Model For The Synthesis Of 3D Faces (1999)</b> [[Paper]](http://gravis.dmi.unibas.ch/publications/Sigg99/morphmod2.pdf)[[Code]](https://github.com/MichaelMure/3DMM)
<p align="center"><img width="40%" src="http://mblogthumb3.phinf.naver.net/MjAxNzAzMTdfMjcz/MDAxNDg5NzE3MzU0ODI3.9lQioLxwoGmtoIVXX9sbVOzhezoqgKMKiTovBnbUFN0g.sXN5tG4Kohgk7OJEtPnux-mv7OAoXVxxCyo3SGZMc6Yg.PNG.atelierjpro/031717_0222_DataDrivenS4.png?type=w420" /></p>
<b>FLAME: Faces Learned with an Articulated Model and Expressions (2017)</b> [[Paper]](https://ps.is.tuebingen.mpg.de/uploads_file/attachment/attachment/400/paper.pdf)[[Code (Chumpy)]](https://github.com/Rubikplayer/flame-fitting)[[Code (TF)]](https://github.com/TimoBolkart/TF_FLAME)
<br>[FLAME](http://flame.is.tue.mpg.de/) is a lightweight and expressive generic head model learned from over 33,000 of accurately aligned 3D scans. The model combines a linear identity shape space (trained from 3800 scans of human heads) with an articulated neck, jaw, and eyeballs, pose-dependent corrective blendshapes, and additional global expression blendshapes.
The code demonstrates how to 1) reconstruct textured 3D faces from images, 2) fit the model to 3D landmarks or registered 3D meshes, or 3) generate 3D face templates for [speech-driven facial animation](https://github.com/TimoBolkart/voca).
<p align="center"> <img width="50%" src="https://github.com/TimoBolkart/TF_FLAME/blob/master/gifs/model_variations.gif"></p>
<b>The Space of Human Body Shapes: Reconstruction and Parameterization from Range Scans (2003)</b> [[Paper]](http://grail.cs.washington.edu/projects/digital-human/pub/allen03space-submit.pdf)
<p align="center"><img width="50%" src="https://ai2-s2-public.s3.amazonaws.com/figures/2016-11-08/46d39b0e21ae956e4bcb7a789f92be480d45ee12/7-Figure10-1.png" /></p>