summaryrefslogtreecommitdiff
path: root/README.md
diff options
context:
space:
mode:
Diffstat (limited to 'README.md')
-rwxr-xr-xREADME.md55
1 files changed, 55 insertions, 0 deletions
diff --git a/README.md b/README.md
new file mode 100755
index 0000000..b0d119f
--- /dev/null
+++ b/README.md
@@ -0,0 +1,55 @@
+<img src='imgs/teaser_720.gif' align="right" width=360>
+
+<br><br><br><br>
+
+# pix2pixHD
+### [[Project]](https://tcwang0509.github.io/pix2pixHD/) [[Paper]](https://arxiv.org/) <br>
+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. <br><br>
+[High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://tcwang0509.github.io/pix2pixHD/)
+ Ting-Chun Wang<sup>1</sup>, Ming-Yu Liu<sup>1</sup>, Jun-Yan Zhu<sup>2</sup>, Andrew Tao<sup>1</sup>, Jan Kautz<sup>1</sup>, Bryan Catanzaro<sup>1</sup>
+ <sup>1</sup>NVIDIA Corporation, <sup>2</sup>UC Berkeley
+ In arxiv, 2017.
+
+## Release notice
+Due to some unexpected delay, we have not got the approval from NVIDIA to release the code yet.<br>
+We are working on it and it should be resolved in a couple of days.<br>
+If you want to get notified once the code is released, please subscribe [here](https://tcwang0509.github.io/pix2pixHD/subscribe.html)
+
+## Image-to-image translation at 2k/1k resolution
+- Our label-to-streetview results
+<p align='center'>
+ <img src='imgs/teaser_label.png' width='440'/>
+ <img src='imgs/teaser_ours.jpg' width='440'/>
+</p>
+- Interactive editing results
+<p align='center'>
+ <img src='imgs/teaser_style.gif' width='440'/>
+ <img src='imgs/teaser_label.gif' width='440'/>
+</p>
+- Additional streetview results
+<p align='center'>
+ <img src='imgs/cityscapes_1.jpg' width='440'/>
+ <img src='imgs/cityscapes_2.jpg' width='440'/>
+</p>
+<p align='center'>
+ <img src='imgs/cityscapes_3.jpg' width='440'/>
+ <img src='imgs/cityscapes_4.jpg' width='440'/>
+</p>
+
+- Label-to-face and interactive editing results
+<p align='center'>
+ <img src='imgs/face1_1.jpg' width='290'/>
+ <img src='imgs/face1_2.jpg' width='290'/>
+ <img src='imgs/face1_3.jpg' width='290'/>
+</p>
+<p align='center'>
+ <img src='imgs/face2_1.jpg' width='290'/>
+ <img src='imgs/face2_2.jpg' width='290'/>
+ <img src='imgs/face2_3.jpg' width='290'/>
+</p>
+
+- Our editing interface
+<p align='center'>
+ <img src='imgs/city_short.gif' width='380'/>
+ <img src='imgs/face_short.gif' width='490'/>
+</p>