Frequency Separation for Real-World Super-Resolution

by   Manuel Fritsche, et al.

Most of the recent literature on image super-resolution (SR) assumes the availability of training data in the form of paired low resolution (LR) and high resolution (HR) images or the knowledge of the downgrading operator (usually bicubic downscaling). While the proposed methods perform well on standard benchmarks, they often fail to produce convincing results in real-world settings. This is because real-world images can be subject to corruptions such as sensor noise, which are severely altered by bicubic downscaling. Therefore, the models never see a real-world image during training, which limits their generalization capabilities. Moreover, it is cumbersome to collect paired LR and HR images in the same source domain. To address this problem, we propose DSGAN to introduce natural image characteristics in bicubically downscaled images. It can be trained in an unsupervised fashion on HR images, thereby generating LR images with the same characteristics as the original images. We then use the generated data to train a SR model, which greatly improves its performance on real-world images. Furthermore, we propose to separate the low and high image frequencies and treat them differently during training. Since the low frequencies are preserved by downsampling operations, we only require adversarial training to modify the high frequencies. This idea is applied to our DSGAN model as well as the SR model. We demonstrate the effectiveness of our method in several experiments through quantitative and qualitative analysis. Our solution is the winner of the AIM Challenge on Real World SR at ICCV 2019.


page 1

page 3

page 6

page 7

page 8


Toward Real-World Super-Resolution via Adaptive Downsampling Models

Most image super-resolution (SR) methods are developed on synthetic low-...

Toward Real-World Light Field Super-Resolution

Deep learning has opened up new possibilities for light field super-reso...

Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution

Due to the sophisticated imaging process, an identical scene captured by...

Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training

These days, unsupervised super-resolution (SR) has been soaring due to i...

Adversarial training with cycle consistency for unsupervised super-resolution in endomicroscopy

In recent years, endomicroscopy has become increasingly used for diagnos...

Frequency Consistent Adaptation for Real World Super Resolution

Recent deep-learning based Super-Resolution (SR) methods have achieved r...

Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution

Most current deep learning based single image super-resolution (SISR) me...

Code Repositories


[ICCVW 2019] PyTorch implementation of DSGAN and ESRGAN-FS from the paper "Frequency Separation for Real-World Super-Resolution". This code was the winning solution of the AIM challenge on Real-World Super-Resolution at ICCV 2019

view repo


Training and Testing codes for our paper "Real-world Image Super-resolution via Domain-distance Aware Training"

view repo

Please sign up or login with your details

Forgot password? Click here to reset