Photo-Realistic Facial Details Synthesis from Single Image

Chen, Anpei; Chen, Zhang; Zhang, Guli; Zhang, Ziheng; Mitchell, Kenny; Yu, Jingyi

Abstract

We present a single-image 3D face synthesis technique that can handle challenging facial expressions while recovering fine geometric details. Our technique employs expression analysis for proxy face geometry generation and combines supervised and unsupervised learning for facial detail synthesis. On proxy generation, we conduct emotion prediction to determine a new expression-informed proxy. On detail synthesis, we present a Deep Facial Detail Net (DFDN) based on Conditional Generative Adversarial Net (CGAN) that employs both geometry and appearance loss functions. For geometry, we capture 366 high-quality 3D scans from 122 different subjects under 3 facial expressions. For appearance, we use additional 20K in-the-wild face images and apply image-based rendering to accommodate lighting variations. Comprehensive experiments demonstrate that our framework can produce high-quality 3D faces with realistic details under challenging facial expressions.

Citation

Chen, A., Chen, Z., Zhang, G., Zhang, Z., Mitchell, K., & Yu, J. (2019, October). Photo-Realistic Facial Details Synthesis from Single Image. Presented at 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
• Start Date: Oct 27, 2019
• End Date: Nov 2, 2019
• Online Publication Date: Feb 27, 2020
• Publication Date: 2019
• Deposit Date: Apr 2, 2019
• Publicly Available Date: Apr 3, 2019
• Publisher: Institute of Electrical and Electronics Engineers
• Pages: 9429-9439
• Series ISSN: 2380-7504
• Book Title: 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
• DOI: https://doi.org/10.1109/ICCV.2019.00952
• Public URL: http://researchrepository.napier.ac.uk/Output/1702421