FaceScape
This is the project page for our paper "FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction", which will appear in CVPR 2020.
FaceScape dataset provides 18,760 textured 3D faces, captured from 938 subjects and each with 20 specific expressions. The 3D models contain high-quality facial geometry that is also processed to be topologically uniformed. Please refer to arXiv paper for more details.
Currently, we are building the website for data release, which is scheduled to be completed by June 2020 (this was slightly delayed due to the COVID-19 outbreaks). We will keep on updating the latest information on this page, and try to release the dataset as soon as possible.
ChangeLog
- 2020/3/31 The pre-print paper is available on Arxiv.