Frequency Consistent Adaptation for Real World Super Resolution

TL;DR

This paper introduces a Frequency Consistent Adaptation method that aligns the frequency domain characteristics of training data with real-world images, significantly improving super-resolution performance in practical scenarios.

Contribution

It proposes a novel Frequency Consistent Adaptation framework that estimates degradation kernels and enforces frequency domain consistency for real-world super-resolution.

Findings

Achieves state-of-the-art results on real-world SR benchmarks.

Improves fidelity and perceptual quality of super-resolved images.

Effectively narrows the domain gap caused by real-world degradations.

Abstract

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.