Photo-Realistic Facial Details Synthesis from Single Image

TL;DR

This paper introduces a novel single-image 3D face synthesis method that captures fine geometric details and handles challenging expressions by combining expression analysis, supervised learning, and a specialized deep neural network.

Contribution

It proposes a new framework integrating expression-informed proxy generation and a Deep Facial Detail Net using CGANs for detailed 3D face synthesis from a single image.

Findings

Produces high-quality 3D faces with realistic details

Handles challenging facial expressions effectively

Utilizes a large dataset of 3D scans and in-the-wild images

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.