Pytorch implementation for high-resolution (e.g. 2048x1024) photorealistic image-to-image translation, for example, turning semantic label maps into photo-realistic images, or synthesizing portraits from face label maps.
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
In arxiv, 2017.
The code is ready to publish but still under final approval process. It should be approved in a couple of days.
If you want to get notified once the code is released, please subscribe here.
- Our label-to-streetview results
- Label-to-face and interactive editing results
- Our editing interface
