FaceScape

This is the project page for our paper "FaceScape: a Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction". [CVPR2020 paper] [supplemetary]

We will also update latest progress and available sources to this repository~ [latest update: 2020/7/25]

Dataset

The datasets are released in website: https://facescape.nju.edu.cn/.

The available sources include:

Item	Description	Quantity	Quality
TU models	Topologically uniformed 3D face models with displacement map and texture map.	16940 models (847 id × 20 exp)	Detailed geometry, 4K dp/tex maps
Multi-view data	Multi-view images, camera paramters and coresponding 3D face mesh.	>400k images (359 id × 20 exp × ≈60 view)	4M~12M pixels
Bilinear model	The statistical model to transform the base shape into the vector space.	4 for different settings	Only for base shape.
Info list	Gender / age of the subjects.	847 subjects	--
Tools	Python code to generate depth map, landmarks, facial segmentation, etc.	--	--

The datasets are only released for non-commercial research use. As facial data involves the privacy of participants, we use strict license terms to ensure that the dataset is not abused. Please visit the website for more information.

Tools

mview - parse and test multi-view images and corresponding 3D models.
bilinear model - simple demo to use facescape bilinear model.
landmark - extract landmarks using predefined vertex index.
extract face - extract facial region from the mesh of full head.

Code

Code of 'detailed riggable 3D face prediction' will be released soon.

ChangeLog

2020/7/25
Multi-view data is available for download, check it here.
Bilinear model with vertex-color has been added to v1.3, check it here.
Info list including gender and age is available in download page.
Tools and samples are added to this repository.
2020/7/7
Bilinear model v1.2 is updated, check it here.
2020/6/13
The website of FaceScape is online.
3D models and bilinear models are available for download.
2020/3/31
The pre-print paper is available on arXiv.

Bibtex

@InProceedings{yang2020facescape,
  author = {Yang, Haotian and Zhu, Hao and Wang, Yanru and Huang, Mingkai and Shen, Qiu and Yang, Ruigang and Cao, Xun},
  title = {FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2020},
  page = {601--610}}

shicaiyuan/facescape