A TensorFlow-based image super-resolution model considering both quantitative and perceptual quality
Switch branches/tags
Nothing to show
Clone or download
Latest commit 67b5f35 Sep 17, 2018
Permalink
Failed to load latest commit information.
figures Reduce figure size Sep 12, 2018
test Add codes and files for testing Sep 12, 2018
.gitignore Initial commit Sep 12, 2018
LICENSE Initial commit Sep 12, 2018
README.md Update README.md Sep 17, 2018

README.md

4PP-EUSR

Four-pass perceptual super-resolution with enhanced upscaling

Introduction

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 for Region 2 in the PIRM Challenge on Perceptual Super Resolution at ECCV 2018.

BSD100 - 37073 ※ 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.

Method PSNR (dB) (↓) Perceptual Index
EDSR 27.796 5.326
MDSR 27.771 5.424
EUSR 27.674 5.307
SRResNet-MSE 27.601 5.217
4PP-EUSR (PIRM Challenge) 26.569 2.683
SRResNet-VGG22 26.322 5.183
SRGAN-MSE 25.981 2.802
Bicubic interpolation 25.957 6.995
SRGAN-VGG22 25.697 2.631
SRGAN-VGG54 25.176 2.351
CX 24.581 2.250

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

Dependencies

  • Python 3.6+
  • TensorFlow 1.8+

Test pre-trained models

Generating upscaled images from the trained models can be done by test/test.py. Following are the brief instructions.

  1. Download and copy the trained model available in Downloads section to the test/ folder.
  2. Place the low-resolution images (PNG only) to the test/LR/ folder.
  3. Run python test.py --model_name [model file name]. For example, if you downloaded the PIRM Challenge version of our pre-trained model, run python test.py --model_name 4pp_eusr_pirm.pb.
  4. The upscaled images will be available on the test/SR/ folder.

Please run python test.py --help for more information.

Training 4PP-EUSR

Currently, the training code is not available. We are working hard on writing the training code for public, so please stay tuned for further updates. :)

Downloads

Pre-trained models:

Results (Set5, Set14, BSD100, PIRM):