High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Ting-Chun Wang1 Ming-Yu Liu1 Jun-Yan Zhu2 Andrew Tao1 Jan Kautz1 Bryan Catanzaro1
1NVIDIA Corporation 2UC Berkeley
[Paper] [Code] [Slides]
![](/web/20210415004515im_/https://tcwang0509.github.io/pix2pixHD/images/teaser_960.gif)
Abstract
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 2048x1024 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.
![paper thumbnail](/web/20210415004515im_/https://tcwang0509.github.io/pix2pixHD/images/paper_thumbnail.jpg)
Paper
CVPR, 2018.
Citation
Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. "High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs", in CVPR, 2018. Bibtex
Code: Pytorch
Our User Interface and Comparisons |
|
Example Results
Semantic labels → Cityscapes street views |
|
![]() |
![]() |
Interactive editing results |
|
![]() |
![]() |
Additional streetview results |
|
![]() |
![]() |
![]() |
![]() |
Label → Face & Interactive Editing Results |
||
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
Our Editing Interface |
|
![]() |
![]() |
Acknowledgement
We thank Taesung Park, Phillip Isola, Tinghui Zhou, Richard Zhang, Rafael Valle and Alexei A. Efros for helpful comments. We also thank Chen and Koltun and Isola et al. for sharing their code. JYZ is supported by a Facebook graduate fellowship.