# Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution

arXiv: https://arxiv.org/abs/2110.12151 · HTML: https://mlsanity.com/paper/2110.12151/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 23 Oct 2021.

## Builds on (most cited first, 23 of 23)

- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [Blind Super-Resolution With Iterative Kernel Correction](https://mlsanity.com/paper/1904.03377/) (2019)
- [Blind Super-Resolution Kernel Estimation using an Internal-GAN](https://mlsanity.com/paper/1909.06581/) (2019)
- [FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors](https://mlsanity.com/paper/1711.10703/) (2017)
- [Unfolding the Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2010.02631/) (2020)
- [StructureFlow: Image Inpainting via Structure-aware Appearance Flow](https://mlsanity.com/paper/1908.03852/) (2019)
- [Structure-Preserving Super Resolution with Gradient Guidance](https://mlsanity.com/paper/2003.13081/) (2020)
- [Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels](https://mlsanity.com/paper/1903.12529/) (2019)
- [Flow-based Kernel Prior with Application to Blind Super-Resolution](https://mlsanity.com/paper/2103.15977/) (2021)
- [Unpaired Image Super-Resolution using Pseudo-Supervision](https://mlsanity.com/paper/2002.11397/) (2020)
- [Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations](https://mlsanity.com/paper/2004.06965/) (2020)
- [Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-Resolvers](https://mlsanity.com/paper/1912.00157/) (2019)
- [Nuclear Norm based Matrix Regression with Applications to Face Recognition with Occlusion and Illumination Changes](https://mlsanity.com/paper/1405.1207/) (2014)
- [Phase-only Image Based Kernel Estimation for Single-image Blind Deblurring](https://mlsanity.com/paper/1811.10185/) (2018)
- [Frequency Consistent Adaptation for Real World Super Resolution](https://mlsanity.com/paper/2012.10102/) (2020)

## Built on by (most cited first, 7 of 7)

- [Deep Constrained Least Squares for Blind Image Super-Resolution](https://mlsanity.com/paper/2202.07508/) (2022)
- [Incorporating Degradation Estimation in Light Field Spatial Super-Resolution](https://mlsanity.com/paper/2405.07012/) (2024)
- [Joint Learning Content and Degradation Aware Feature for Blind Super-Resolution](https://mlsanity.com/paper/2208.13436/) (2022)
- [BlindDiff: Empowering Degradation Modelling in Diffusion Models for Blind Image Super-Resolution](https://mlsanity.com/paper/2403.10211/) (2024)
- [Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation](https://mlsanity.com/paper/2404.16564/) (2024)
- [A Close Look at Few-shot Real Image Super-resolution from the Distortion Relation Perspective](https://mlsanity.com/paper/2111.13078/) (2021)
- [Two Heads Better than One: Dual Degradation Representation for Blind Super-Resolution](https://mlsanity.com/paper/2511.16963/) (2025)

## Abstract (arXiv)

Deep-learning based Super-Resolution (SR) methods have exhibited promising performance under non-blind setting where blur kernel is known. However, blur kernels of Low-Resolution (LR) images in different practical applications are usually unknown. It may lead to significant performance drop when degradation process of training images deviates from that of real images. In this paper, we propose a novel blind SR framework to super-resolve LR images degraded by arbitrary blur kernel with accurate kernel estimation in frequency domain. To our best knowledge, this is the first deep learning method which conducts blur kernel estimation in frequency domain. Specifically, we first demonstrate that feature representation in frequency domain is more conducive for blur kernel reconstruction than in spatial domain. Next, we present a Spectrum-to-Kernel (S2K) network to estimate general blur kernels in diverse forms. We use a Conditional GAN (CGAN) combined with SR-oriented optimization target to learn the end-to-end translation from degraded images' spectra to unknown kernels. Extensive experiments on both synthetic and real-world images demonstrate that our proposed method sufficiently reduces blur kernel estimation error, thus enables the off-the-shelf non-blind SR methods to work under blind setting effectively, and achieves superior performance over state-of-the-art blind SR methods, averagely by 1.39dB, 0.48dB on commom blind SR setting (with Gaussian kernels) for scales 2× and 4×, respectively.