# Blind Super-Resolution Kernel Estimation using an Internal-GAN

arXiv: https://arxiv.org/abs/1909.06581 · HTML: https://mlsanity.com/paper/1909.06581/

## Key facts

- Cited by 175 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2019.

## Built on by (most cited first, 30 of 175)

- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)
- [The Role of ImageNet Classes in Fr'echet Inception Distance](https://mlsanity.com/paper/2203.06026/) (2022)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [The Low-Rank Simplicity Bias in Deep Networks](https://mlsanity.com/paper/2103.10427/) (2021)
- [Blind Image Super-Resolution: A Survey and Beyond](https://mlsanity.com/paper/2107.03055/) (2021)
- [Flow-based Kernel Prior with Application to Blind Super-Resolution](https://mlsanity.com/paper/2103.15977/) (2021)
- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2203.16262/) (2022)
- [Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution](https://mlsanity.com/paper/2108.05302/) (2021)
- [Deep Constrained Least Squares for Blind Image Super-Resolution](https://mlsanity.com/paper/2202.07508/) (2022)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [Reflash Dropout in Image Super-Resolution](https://mlsanity.com/paper/2112.12089/) (2021)
- [Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution](https://mlsanity.com/paper/2309.00287/) (2023)
- [Cross-Quality LFW: A Database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/2108.10290/) (2021)
- [MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution](https://mlsanity.com/paper/2205.05065/) (2022)
- [Blind Image Super-Resolution via Contrastive Representation Learning](https://mlsanity.com/paper/2107.00708/) (2021)
- [Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network](https://mlsanity.com/paper/2104.09556/) (2021)
- [DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows](https://mlsanity.com/paper/2101.05796/) (2021)
- [Unsupervised Deraining: Where Contrastive Learning Meets Self-similarity](https://mlsanity.com/paper/2203.11509/) (2022)
- [Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel](https://mlsanity.com/paper/2107.00986/) (2021)
- [Learning the Degradation Distribution for Blind Image Super-Resolution](https://mlsanity.com/paper/2203.04962/) (2022)
- [Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution](https://mlsanity.com/paper/2108.01070/) (2021)
- [Diffusion-based Blind Text Image Super-Resolution](https://mlsanity.com/paper/2312.08886/) (2023)
- [Variational Deep Image Restoration](https://mlsanity.com/paper/2207.01074/) (2022)
- [Learning Generative Structure Prior for Blind Text Image Super-resolution](https://mlsanity.com/paper/2303.14726/) (2023)
- [AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos](https://mlsanity.com/paper/2206.07038/) (2022)
- [Image Super-Resolution with Text Prompt Diffusion](https://mlsanity.com/paper/2311.14282/) (2023)
- [A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds](https://mlsanity.com/paper/2205.04910/) (2022)

## Abstract (arXiv)

Super resolution (SR) methods typically assume that the low-resolution (LR) image was downscaled from the unknown high-resolution (HR) image by a fixed 'ideal' downscaling kernel (e.g. Bicubic downscaling). However, this is rarely the case in real LR images, in contrast to synthetically generated SR datasets. When the assumed downscaling kernel deviates from the true one, the performance of SR methods significantly deteriorates. This gave rise to Blind-SR - namely, SR when the downscaling kernel ("SR-kernel") is unknown. It was further shown that the true SR-kernel is the one that maximizes the recurrence of patches across scales of the LR image. In this paper we show how this powerful cross-scale recurrence property can be realized using Deep Internal Learning. We introduce "KernelGAN", an image-specific Internal-GAN, which trains solely on the LR test image at test time, and learns its internal distribution of patches. Its Generator is trained to produce a downscaled version of the LR test image, such that its Discriminator cannot distinguish between the patch distribution of the downscaled image, and the patch distribution of the original LR image. The Generator, once trained, constitutes the downscaling operation with the correct image-specific SR-kernel. KernelGAN is fully unsupervised, requires no training data other than the input image itself, and leads to state-of-the-art results in Blind-SR when plugged into existing SR algorithms.