Frequency Consistent Adaptation for Real World Super Resolution

12/18/2020
by   Xiaozhong Ji, et al.
6

Recent deep-learning based Super-Resolution (SR) methods have achieved remarkable performance on images with known degradation. However, these methods always fail in real-world scene, since the Low-Resolution (LR) images after the ideal degradation (e.g., bicubic down-sampling) deviate from real source domain. The domain gap between the LR images and the real-world images can be observed clearly on frequency density, which inspires us to explictly narrow the undesired gap caused by incorrect degradation. From this point of view, we design a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying existing SR methods to the real scene. We estimate degradation kernels from unsupervised images and generate the corresponding LR images. To provide useful gradient information for kernel estimation, we propose Frequency Density Comparator (FDC) by distinguishing the frequency density of images on different scales. Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models. Extensive experiments show that the proposed FCA improves the performance of the SR model under real-world setting achieving state-of-the-art results with high fidelity and plausible perception, thus providing a novel effective framework for real-world SR application.

READ FULL TEXT

page 1

page 2

page 4

page 6

page 7

research
01/08/2020

Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation

Most learning-based super-resolution (SR) methods aim to recover high-re...
research
11/03/2021

Resampling and super-resolution of hexagonally sampled images using deep learning

Super-resolution (SR) aims to increase the resolution of imagery. Applic...
research
04/19/2021

Kernel Agnostic Real-world Image Super-resolution

Recently, deep neural network models have achieved impressive results in...
research
05/13/2022

Unsupervised Representation Learning for 3D MRI Super Resolution with Degradation Adaptation

High-resolution (HR) MRI is critical in assisting the doctor's diagnosis...
research
11/18/2019

Frequency Separation for Real-World Super-Resolution

Most of the recent literature on image super-resolution (SR) assumes the...
research
10/14/2022

Blind Super-Resolution for Remote Sensing Images via Conditional Stochastic Normalizing Flows

Remote sensing images (RSIs) in real scenes may be disturbed by multiple...
research
07/31/2022

Robust Real-World Image Super-Resolution against Adversarial Attacks

Recently deep neural networks (DNNs) have achieved significant success i...

Please sign up or login with your details

Forgot password? Click here to reset