Recent deep image generation models, such as StyleGAN2, face challenges to produce high-quality 2D face images with multi-view consistency. We address this issue by proposing an approach for generating detailed 3D faces using a pre-trained StyleGAN2 model. Our method estimates the 3D Morphable Model (3DMM) coefficients directly from the StyleGAN2's stylecode. To add more details to the produced 3D face models, we train a generator to produce two UV maps: a diffuse map to give the model a more faithful appearance and a generalized displacement map to add geometric details to the model. To achieve multi-view consistency, we also add a symmetric view image to recover information regarding the invisible side of a single image. The generated detailed 3D face models allow for consistent changes in viewing angles, expressions, and lighting conditions. Experimental results indicate that our method outperforms previous approaches both qualitatively and quantitatively.

@article{ chung_stylefaceuv,	      
author    = {Wei-Chieh Chung and Jian-Kai Zhu and I-Chao Shen and Yu-Ting Wu and Yung-Yu Chuang},
title     = {StyleFaceUV: a 3D Face UV Map Generator for View-Consistent Face Image Synthesis},
journal   = {British Machine Vision Conference (BMVC)},
year      = {2022}
}