Home

Awesome

Practical Single-Image Super-Resolution Using Look-Up Table

[Paper]

Dependency

1. Training deep SR network

  1. Move into a directory.
cd ./1_Train_deep_model
  1. Prepare DIV2K training images into ./train.
  1. Set5 HR/LR validation png images are already included in ./val, or you can use other images.

  2. You may modify user parameters in L22 in ./Train_Model_S.py.

  3. Run.

python Train_Model_S.py
  1. Checkpoints will be saved in ./checkpoint/S.

2. Transferring to LUT

  1. Move into a directory.
cd ./2_Transfer_to_LUT
  1. Modify user parameters in L9 in ./Transfer_Model_S.py.
  1. Run.
python Transfer_Model_S.py
  1. The resulting LUT will be saved like ./Model_S_x4_4bit_int8.npy.

3. Testing using LUT

  1. Move into a directory.
cd ./3_Test_using_LUT
  1. Modify user parameters in L17 in ./Test_Model_S.py.
  1. Set5 HR/LR test images are already included in ./test, or you can use other images.

  2. Run.

python Test_Model_S.py      # Ours-S
python Test_Model_F.py      # Ours-F
python Test_Model_V.py      # Ours-V
  1. Resulting images will be saved in ./output_S_x4_4bit/*.png.

  2. We can reproduce the results of Table 6 in the paper, by modifying the variable SAMPLING_INTERVAL in L19 in Test_Model_S.py to range 3-8.

4. Testing on a smartphone

  1. Download SR-LUT.apk and install it.

  2. You can test Set14 images or other images.

SR-LUT Android app demo

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}
}