SR-LUT
Practical Single-Image Super-Resolution Using Look-Up Table
Dependency
- Python 3.6
- PyTorch
- glob
- numpy
- pillow
- tqdm
- tensorboardx
1. Training deep SR network
- Move into a directory.
cd ./1_Train_deep_model
- Prepare DIV2K training images into
./train.
- HR images should be placed as
./train/DIV2K_train_HR/*.png. - LR images should be placed as
./train/DIV2K_train_LR_bicubic/X4/*.png.
-
Set5 HR/LR validation png images are already included in
./val, or you can use other images. -
You may modify user parameters in L22 in
./Train_Model_S.py. -
Run.
python Train_Model_S.py
- Checkpoints will be saved in
./checkpoint/S.
- Training log will be generated in
./log/S.
2. Transferring to LUT
- Move into a directory.
cd ./2_Transfer_to_LUT
- Modify user parameters in L9 in
./Transfer_Model_S.py.
- Specify a saved checkpoint in the step 1, or you can use attached
./Model_S.pth.
- Run.
python Transfer_Model_S.py
- The resulting LUT will be saved like
./Model_S_x4_4bit_int8.npy.
3. Testing using LUT
- Move into a directory.
cd ./3_Test_using_LUT
- Modify user parameters in L17 in
./Test_Model_S.py.
- Specify the generated LUT in the step 2, or use attached LUTs (npy files).
-
Set5 HR/LR test images are already included in
./test, or you can use other images. -
Run.
python Test_Model_S.py # Ours-S
python Test_Model_F.py # Ours-F
python Test_Model_V.py # Ours-V
-
Resulting images will be saved in
./output_S_x4_4bit/*.png. -
We can reproduce the results of Table 6 in the paper, by modifying the variable
SAMPLING_INTERVALin L19 in Test_Model_S.py to range 3-8.
4. Testing on a smartphone
-
Download SR-LUT.apk and install it.
-
You can test Set14 images or other images.
BibTeX
@InProceedings{jo2021practical,
author = {Jo, Younghyun and Kim, Seon Joo},
title = {Practical Single-Image Super-Resolution Using Look-Up Table},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021}
}
