deepaiorg/tf-super-resolution repository overview

⁠Super Resolution: 4PP-EUSR

⁠

This model has been integrated with ai_integration⁠ for seamless portability across hosting providers.

Four-pass perceptual super-resolution with enhanced upscaling

⁠Overview

This repository contains a TensorFlow-based implementation of 4PP-EUSR ("Deep learning-based image super-resolution considering quantitative and perceptual quality")⁠, which considers both the quantitative (e.g., PSNR) and perceptual quality (e.g., NIQE) of the upscaled images. Our method won the 2nd place and got the highest human opinion score for Region 2 in the 2018 PIRM Challenge on Perceptual Image Super-resolution at ECCV 2018⁠.

Nvidia-Docker is required to run this image.

⁠For details see Super Resolution⁠ on Deep AI⁠

⁠Quick Start

docker pull deepaiorg/tf-super-resolution

⁠HTTP

nvidia-docker run --rm -it -e MODE=http -p 5000:5000 deepaiorg/tf-super-resolution

Open your browser to localhost:5000 (or the correct IP address)

⁠Command Line

Save your image as content.jpg in the current directory.

nvidia-docker run --rm -it -v `pwd`:/shared -e MODE=command_line deepaiorg/tf-super-resolution --image /shared/content.jpg --output /shared/output.jpg

⁠Docker build

docker build -t tf-super-resolution .

⁠Introduction

※ The perceptual index is calculated by "0.5 * ((10 - Ma⁠) + NIQE⁠)", which is used in the PIRM Challenge⁠. Lower is better.

Followings are the performance comparison evaluated on the BSD100⁠ dataset.

Please cite following papers when you use the code, pre-trained models, or results:

• J.-H. Choi, J.-H. Kim, M. Cheon, J.-S. Lee: Deep learning-based image super-resolution considering quantitative and perceptual quality. arXiv:1809.04789 (2018) [arXiv]⁠

@article{choi2018deep,
  title={Deep learning-based image super-resolution considering quantitative and perceptual quality},
  author={Choi, Jun-Ho and Kim, Jun-Hyuk and Cheon, Manri and Lee, Jong-Seok},
  journal={arXiv preprint arXiv:1809.04789},
  year={2018}
}

• J.-H. Kim, J.-S. Lee: Deep residual network with enhanced upscaling module for super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 913-921 (2018) [Paper]⁠

@inproceedings{kim2018deep,
  title={Deep residual network with enhanced upscaling module for super-resolution},
  author={Kim, Jun-Hyuk and Lee, Jong-Seok},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  year={2018}
}