Can I read 3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation on EtoBox?

3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation by Tang, Junshu; Zhang, Bo; Yang, Binxin; Zhang, Ting; Chen, Dong; Ma, Lizhuang; Wen, Fang is a scholarly article available to read on EtoBox.

What is 3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation about?

In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs. While plenty of works extend unconditional generative models and achieve some levels of controllability, it is still challenging to ensure multi-view consistency, especially in large poses. In this work, we propose a network that generates 3D-aware portraits while being controllable according to semantic parameters regarding pose, identity, expression and illumination. Our network uses neural scene representation to model 3D-aware portraits, whose generation is guided by a parametric face model that supports explicit control. While the latent disentanglement can be further enhanced by contrasting images with partially different attributes, there still exists noticeable inconsistency in non-face areas, e.g., hair and background, when animating expressions. Wesolve this by proposing a volume blending strategy in which we form a composite output by blending dynamic and static areas, with two parts segmented from the jointly learned semantic field. Our method outperforms prior arts in extensive experiments, producin

Author

Tang, Junshu; Zhang, Bo; Yang, Binxin; Zhang, Ting; Chen, Dong; Ma, Lizhuang; Wen, Fang

Published

2022

Language

EN