# Frequency Consistent Adaptation for Real World Super Resolution

arXiv: https://arxiv.org/abs/2012.10102 · HTML: https://mlsanity.com/paper/2012.10102/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution](https://mlsanity.com/paper/2110.12151/) (2021)
- [Universal Image Restoration Pre-training via Masked Degradation Classification](https://mlsanity.com/paper/2510.13282/) (2025)
- [Toward Real-World Light Field Super-Resolution](https://mlsanity.com/paper/2305.18994/) (2023)
- [Unpaired Optical Coherence Tomography Angiography Image Super-Resolution via Frequency-Aware Inverse-Consistency GAN](https://mlsanity.com/paper/2309.17269/) (2023)
- [Bridging Degradation Discrimination and Generation for Universal Image Restoration](https://mlsanity.com/paper/2602.00579/) (2026)
- [LensBridge: Frequency-Guided Compound Degradation Adaptation for Lens Aberration Correction and Veiling Glare Removal](https://mlsanity.com/paper/2610.00318/) (2026)

## Abstract (arXiv)

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.