Photo-Realistic Facial Details Synthesis from Single Image
This addresses the need for realistic 3D face generation in applications like animation or VR, but it is incremental as it builds on existing proxy and GAN methods.
The paper tackles the problem of synthesizing photo-realistic 3D facial details from a single image, especially under challenging expressions, by using expression analysis and a deep learning model, resulting in high-quality 3D faces as demonstrated in experiments.
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.