Image-to-Image Translation with Conditional Adversarial Networks

被引：12442

作者：

Isola, Phillip ^{[1
]}

Zhu, Jun-Yan ^{[1
]}

Zhou, Tinghui ^{[1
]}

Efros, Alexei A. ^{[1
]}

机构：

[1] Univ Calif Berkeley, Berkeley AI Res BAIR Lab, Berkeley, CA 94720 USA

来源：

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) | 2017年

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/CVPR.2017.632

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Moreover, since the release of the pix2pix software associated with this paper, hundreds of twitter users have posted their own artistic experiments using our system. As a community, we no longer hand-engineer our mapping functions, and this work suggests we can achieve reasonable results without hand-engineering our loss functions either.

引用

页码：5967 / 5976

页数：10