- Notifications
You must be signed in to change notification settings - Fork1
Reimplementing the paper "SinGAN: Learning a Generative Model from a Single Natural Image"
License
NotificationsYou must be signed in to change notification settings
MingtaoGuo/SinGAN_Pytorch
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Reimplementing the paper "SinGAN: Learning a Generative Model from a Single Natural Image"
- python3
- torch1.1.0
- pillow
- numpy
- imageio
- Modifying the image path in "train.py"
- Executing the file "train.py"
- Random sample from single image, "random_sample_from_single.py"
- Harmonization, "harmonization.py"
- Creating an animation, "animation.py"
- Converting painting to image, "harmonization.py"
| Raw img | random sampled | animation |
|---|---|---|
 |  |  |
 |  |  |
 |  |  |
| Raw img | n=1 | n=2 | n=3 | n=4 |
|---|---|---|---|---|
 |  |  |  |  |
| Raw img | n=5 | n=6 | n=7 | n=8 |
|---|---|---|---|---|
|  |  |  |  |
The results of this code still have some problems. Sometimes, it generates the distortion image. I really don't know how to fix it.
Thanks for thesource code of SinGAN, it's very helpful!
Mingtao Guo
Xi'an University of technology
[1]. Shaham, Tamar Rott, Tali Dekel, and Tomer Michaeli. "Singan: Learning a generative model from a single natural image." Proceedings of the IEEE International Conference on Computer Vision. 2019.