1. [Publications](/index.php/publications)
2. High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
 
 # High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

  ![](/sites/default/files/publications/pix2pixHD.gif) 

 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.



 ## Authors



[Ting-Chun Wang](/index.php/person/ting-chun-wang)

[Ming-Yu Liu](/index.php/person/ming-yu-liu)

Jun-Yan Zhu (University of California Bekerley)

Andrew Tao (NVIDIA)

[Jan Kautz](/index.php/person/jan-kautz)

Bryan Catanzaro (NVIDIA)

 

 

 ## Publication Date



Monday, June 18, 2018

 

 ## Published in



[CVPR](https://arxiv.org/abs/1711.11585)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence)

[Computer Graphics](/index.php/research-area/computer-graphics)

[Computer Vision](/index.php/research-area/computer-vision)

[Generative AI](/index.php/research-area/generative-ai)

 

 

 ## External Links



[Code](https://github.com/NVIDIA/pix2pixHD)

[Demo video](https://www.youtube.com/watch?v=3AIpPlzM_qs&feature=youtu.be)

 

 

 ## Uploaded Files



[arxiv paper](https://research.nvidia.com/sites/default/files/pubs/2017-12_High-Resolution-Image-Synthesis/1711.11585.pdf "Open file in new window")9.23 MB