期刊
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
卷 -, 期 -, 页码 5444-5453出版社
IEEE
DOI: 10.1109/CVPR.2017.578
关键词
-
类别
资金
- NSF [IIS-1161876]
- Partner University Fund 4DVision project
Traditional face editing methods often require a number of sophisticated and task specific algorithms to be applied one after the other - a process that is tedious, fragile, and computationally intensive. In this paper, we propose an end-to-end generative adversarial network that infers a face-specific disentangled representation of intrinsic face properties, including shape (i.e. normals), albedo, and lighting, and an alpha matte. We show that this network can be trained on in-the-wild images by incorporating an in-network physically-based image formation module and appropriate loss functions. Our disentangling latent representation allows for semantically relevant edits, where one aspect of facial appearance can be manipulated while keeping orthogonal properties fixed, and we demonstrate its use for a number of facial editing applications.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据