High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs). Conditional GANs have enabled a variety of applications, but the results are often limited to low-resolution and still far fr...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 8798 - 8807
Main Authors Wang, Ting-Chun, Liu, Ming-Yu, Zhu, Jun-Yan, Tao, Andrew, Kautz, Jan, Catanzaro, Bryan
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Gallium nitride
Generators
Image generation
Image resolution
Semantics
Task analysis
Training
Online AccessGet full text

Cover

More Information
Summary:We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs). Conditional GANs have enabled a variety of applications, but the results are often limited to low-resolution and still far from realistic. In this work, we generate 2048 Ã- 1024 visually appealing results with a novel adversarial loss, as well as new multi-scale generator and discriminator architectures. Furthermore, we extend our framework to interactive visual manipulation with two additional features. First, we incorporate object instance segmentation information, which enables object manipulations such as removing/adding objects and changing the object category. Second, we propose a method to generate diverse results given the same input, allowing users to edit the object appearance interactively. Human opinion studies demonstrate that our method significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00917