This repository contains an op-for-op PyTorch reimplementation of Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network .

• CARN-PyTorch
  • Overview
  • Table of contents
  • Download weights
  • Download datasets
  • How Test and Train
    • Test
    • Train model
    • Resume train model
  • Result
  • Contributing
  • Credit
    • Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network

• Google Driver
• Baidu Driver

Contains DIV2K, DIV8K, Flickr2K, OST, T91, Set5, Set14, BSDS100 and BSDS200, etc.

• Google Driver
• Baidu Driver

Please refer to README.md in the data directory for the method of making a dataset.

Both training and testing only need to modify the config.py file.

• line 31: upscale_factor change to 2.
• line 33: mode change to test.
• line 70: model_path change to results/pretrained_models/CARN_x2-DIV2K-2096ee7f.pth.tar.

• line 31: upscale_factor change to 2.
• line 33: mode change to train.
• line 35: exp_name change to CARN_x2.

• line 31: upscale_factor change to 2.
• line 33: mode change to train.
• line 35: exp_name change to CARN_x2.
• line 48: resume change to samples/CARN_x2/epoch_xxx.pth.tar.

Source of original paper results: https://arxiv.org/pdf/1803.08664v5.pdf

In the following table, the psnr value in () indicates the result of the project, and - indicates no test.

# Download `CARN_x2-DIV2K-4797e51b.pth.tar` weights to `./results/pretrained_models`
# More detail see `README.md<Download weights>`
python ./inference.py --inputs_path ./figure/comic_lr.png --output_path ./figure/comic_sr.png --weights_path ./results/pretrained_models/CARN_x2-DIV2K-4797e51b.pth.tar

Input:

Output:

Build CARN model successfully.
Load CARN model weights `./results/pretrained_models/CARN_x2-DIV2K-4797e51b.pth.tar` successfully.
SR image save to `./figure/comic_sr.png`

If you find a bug, create a GitHub issue, or even better, submit a pull request. Similarly, if you have questions, simply post them as GitHub issues.

I look forward to seeing what the community does with these models!

Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn

Abstract
. In recent years, deep learning methods have been successfully applied to single-image super-resolution tasks. Despite their great performances, deep learning methods cannot be easily applied to realworld applications due to the requirement of heavy computation. In this paper, we address this issue by proposing an accurate and lightweight deep network for image super-resolution. In detail, we design an architecture that implements a cascading mechanism upon a residual network. We also present variant models of the proposed cascading residual network to further improve efficiency. Our extensive experiments show that even with much fewer parameters and operations, our models achieve performance comparable to that of state-of-the-art methods.

[Paper]

@article{DBLP:journals/corr/abs-1803-08664,
  author    = {Namhyuk Ahn and
               Byungkon Kang and
               Kyung{-}Ah Sohn},
  title     = {Fast, Accurate, and, Lightweight Super-Resolution with Cascading Residual
               Network},
  journal   = {CoRR},
  volume    = {abs/1803.08664},
  year      = {2018}
}