😃 Training codes are in BasicSR repo.
By Xintao Wang, Ke Yu, Chao Dong, Chen Change Loy.
This repo only provides simple testing codes - original torch version used in the paper and a pytorch version. For full training and testing codes, please refer to BasicSR.
@InProceedings{wang2018sftgan,
author = {Wang, Xintao and Yu, Ke and Dong, Chao and Loy, Chen Change},
title = {Recovering realistic texture in image super-resolution by deep spatial feature transform},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}
It provides Torch and PyTorch versions. Recommend the PyTorch version.
- Python 3
- PyTorch >= 0.4.0
- Python packages:
pip install numpy opencv-python
- Torch
- Other torch dependencies, e.g.
nngraph
,paths
,image
(install them byluarocks install xxx
)
Note that the SFTGAN model is limited to some outdoor scenes. It is an unsatisfying limitation that we need to relax in future.
- Clone this github repo.
git clone https://github.com/xinntao/SFTGAN
cd SFTGAN
- There are two sample images in the
./data/samples
folder. - Download pretrained models from Google Drive or Baidu Drive. Please see model list for more details.
- First run segmentation test.
[PyTorch]
cd pytorch_test
python test_segmentation.py
[Torch]
cd torch_test
th test_segmentation.lua
The segmentation results are then in ./data
with _segprob
, _colorimg
, _byteimg
suffix.
- Run sftgan test.
[PyTorch]
python test_sftgan.py.
[Torch]
th test_sftgan.lua
The results are in then in ./data
with _result
suffix.
SFT - Spatial Feature Transform (Modulation).
A Spatial Feature Transform (SFT) layer has been proposed to efficiently incorporate the categorical conditions into a CNN network.
There is a fantastic blog explaining the widely-used feature modulation operation distill - Feature-wise transformations.
We have explored the use of semantic segmentation maps as categorical prior for SR.
- Outdoor Scene Train/Test
OST300 300 test images of outdoor scences
Download the OST dataset from Google Drive or Baidu Drive.
😆 Image Viewer - HandyViewer
May try HandyViewer - an image viewer that you can switch image with a fixed zoom ratio, easy for comparing image details.