SRCNN-PyTorch

Overview

This repository contains an op-for-op PyTorch reimplementation of Image Super-Resolution Using Deep Convolutional Networks.

Table of contents

• SRCNN-PyTorch
  • Overview
  • Table of contents
  • Download weights
  • Download datasets
  • How Test and Train
    • Test
    • Train SRCNN model
    • Resume train SRCNN model
  • Result
  • Contributing
  • Credit
    • Image Super-Resolution Using Deep Convolutional Networks

Download weights

• Google Driver
• Baidu Driver

Download datasets

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.

How Test and Train

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

Test

• line 29: upscale_factor change to 2.
• line 31: mode change to test.
• line 66: model_path change to results/pretrained_models/srcnn_x2-T91-7d6e0623.pth.tar.

Train SRCNN model

• line 29: upscale_factor change to 2.
• line 31: mode change to train.
• line 33: exp_name change to SRCNN_x2.

Resume train SRCNN model

• line 31: upscale_factor change to 2.
• line 33: mode change to train.
• line 35: exp_name change to SRCNN_x2.
• line 46: resume change to samples/SRCNN_x2/epoch_xxx.pth.tar.

Result

Source of original paper results: https://arxiv.org/pdf/1501.00092v3.pdf

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

# Download `srcnn_x2-T91-7d6e0623.pth.tar` weights to `./results/pretrained_models`
# More detail see `README.md<Download weights>`
python ./inference.py --inputs_path ./figure/butterfly_lr.png --output_path ./figure/butterfly_sr.png --weights_path ./results/pretrained_models/srcnn_x2-T91-7d6e0623.pth.tar

Input:

Output:

Build SRCNN model successfully.
Load SRCNN model weights `./results/pretrained_models/srcnn_x2-T91-7d6e0623.pth.tar` successfully.
SR image save to `./figure/butterfly_sr.png`

Contributing

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!

Credit

Image Super-Resolution Using Deep Convolutional Networks

Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang

Abstract
We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality.

[Paper] [Author's implements(Caffe)]

@misc{dong2014image,
    title={Image Super-Resolution Using Deep Convolutional Networks},
    author={Chao Dong and Chen Change Loy and Kaiming He and Xiaoou Tang},
    year={2014},
    eprint={1501.00092},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}