This repository contains an op-for-op PyTorch reimplementation of ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks.

• ESRGAN-PyTorch
  • Overview
  • Table of contents
  • Download weights
  • Download datasets
  • How Test and Train
    • Test
    • Train RRDBNet model
    • Resume train RRDBNet model
    • Train ESRGAN model
    • Resume train ESRGAN model
  • Result
  • Contributing
  • Credit
    • ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

• Google Driver
• Baidu Driver

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

• Google Driver
• Baidu Driver

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

• line 31: upscale_factor change to 4.
• line 33: mode change to test.
• line 111: model_path change to results/pretrained_models/RRDBNet_x4-DFO2K-2e2a91f4.pth.tar.

• line 31: upscale_factor change to 4.
• line 33: mode change to train_rrdbnet.
• line 35: exp_name change to RRDBNet_baseline.

• line 31: upscale_factor change to 4.
• line 33: mode change to train_rrdbnet.
• line 35: exp_name change to RRDBNet_baseline.
• line 49: resume change to samples/RRDBNet_baseline/g_epoch_xxx.pth.tar.

• line 31: upscale_factor change to 4.
• line 33: mode change to train_esrgan.
• line 35: exp_name change to ESRGAN_baseline.
• line 77: resume change to results/RRDBNet_baseline/g_last.pth.tar.

• line 31: upscale_factor change to 4.
• line 33: mode change to train_esrgan.
• line 35: exp_name change to ESRGAN_baseline.
• line 77: resume change to results/RRDBNet_baseline/g_last.pth.tar.
• line 78: resume_d change to samples/ESRGAN_baseline/g_epoch_xxx.pth.tar.
• line 79: resume_g change to samples/ESRGAN_baseline/g_epoch_xxx.pth.tar.

Source of original paper results: https://arxiv.org/pdf/1809.00219v2.pdf

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

# Download `ESRGAN_x4-DFO2K-25393df7.pth.tar` weights to `./results/pretrained_models`
# More detail see `README.md<Download weights>`
python ./inference.py --inputs_path ./figure/baboon_lr.png --output_path ./figure/baboon_sr.png --weights_path ./results/pretrained_models/ESRGAN_x4-DFO2K-25393df7.pth.tar

Input:

Output:

Build ESRGAN model successfully.
Load ESRGAN model weights `./results/pretrained_models/ESRGAN_x4-DFO2K-25393df7.pth.tar` successfully.
SR image save to `./figure/baboon_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!

Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Chen Change Loy, Yu Qiao, Xiaoou Tang

Abstract
The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts. To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit. Moreover, we borrow the idea from relativistic GAN to let the discriminator predict relative realness instead of the absolute value. Finally, we improve the perceptual loss by using the features before activation, which could provide stronger supervision for brightness consistency and texture recovery. Benefiting from these improvements, the proposed ESRGAN achieves consistently better visual quality with more realistic and natural textures than SRGAN and won the first place in the PIRM2018-SR Challenge. The code is available at this https URL.

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

@misc{wang2018esrgan,
    title={ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks},
    author={Xintao Wang and Ke Yu and Shixiang Wu and Jinjin Gu and Yihao Liu and Chao Dong and Chen Change Loy and Yu Qiao and Xiaoou Tang},
    year={2018},
    eprint={1809.00219},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}