# Deep learning techniques for blind image super-resolution: A high-scale multi-domain perspective evaluation

arXiv: https://arxiv.org/abs/2306.09426 · HTML: https://mlsanity.com/paper/2306.09426/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 61 references that are in the map.
- First posted on arXiv 15 Jun 2023.

## Builds on (most cited first, 29 of 29)

- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [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)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Deep Learning for Image Super-resolution: A Survey](https://mlsanity.com/paper/1902.06068/) (2019)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [Deep Back-Projection Networks For Super-Resolution](https://mlsanity.com/paper/1803.02735/) (2018)
- [Blind Super-Resolution With Iterative Kernel Correction](https://mlsanity.com/paper/1904.03377/) (2019)
- [VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning](https://mlsanity.com/paper/1705.07761/) (2017)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)
- [Blind Super-Resolution Kernel Estimation using an Internal-GAN](https://mlsanity.com/paper/1909.06581/) (2019)
- [The 2018 PIRM Challenge on Perceptual Image Super-resolution](https://mlsanity.com/paper/1809.07517/) (2018)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [Unfolding the Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2010.02631/) (2020)
- [To learn image super-resolution, use a GAN to learn how to do image degradation first](https://mlsanity.com/paper/1807.11458/) (2018)
- [Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data](https://mlsanity.com/paper/2111.06849/) (2021)
- [NTIRE 2022 Challenge on Perceptual Image Quality Assessment](https://mlsanity.com/paper/2206.11695/) (2022)
- [Deep Cascaded Bi-Network for Face Hallucination](https://mlsanity.com/paper/1607.05046/) (2016)
- [Simultaneous Super-Resolution and Cross-Modality Synthesis of 3D Medical Images using Weakly-Supervised Joint Convolutional Sparse Coding](https://mlsanity.com/paper/1705.02596/) (2017)
- [Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel](https://mlsanity.com/paper/2107.00986/) (2021)
- [Deep Learning -- A first Meta-Survey of selected Reviews across Scientific Disciplines, their Commonalities, Challenges and Research Impact](https://mlsanity.com/paper/2011.08184/) (2020)
- [SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks](https://mlsanity.com/paper/1801.10319/) (2018)

## Abstract (arXiv)

Despite several solutions and experiments have been conducted recently addressing image super-resolution (SR), boosted by deep learning (DL) techniques, they do not usually design evaluations with high scaling factors, capping it at 2x or 4x. Moreover, the datasets are generally benchmarks which do not truly encompass significant diversity of domains to proper evaluate the techniques. It is also interesting to remark that blind SR is attractive for real-world scenarios since it is based on the idea that the degradation process is unknown, and hence techniques in this context rely basically on low-resolution (LR) images. In this article, we present a high-scale (8x) controlled experiment which evaluates five recent DL techniques tailored for blind image SR: Adaptive Pseudo Augmentation (APA), Blind Image SR with Spatially Variant Degradations (BlindSR), Deep Alternating Network (DAN), FastGAN, and Mixture of Experts Super-Resolution (MoESR). We consider 14 small datasets from five different broader domains which are: aerial, fauna, flora, medical, and satellite. Another distinctive characteristic of our evaluation is that some of the DL approaches were designed for single-image SR but others not. Two no-reference metrics were selected, being the classical natural image quality evaluator (NIQE) and the recent transformer-based multi-dimension attention network for no-reference image quality assessment (MANIQA) score, to assess the techniques. Overall, MoESR can be regarded as the best solution although the perceptual quality of the created HR images of all the techniques still needs to improve. Supporting code: https://github.com/vsantjr/DL_BlindSR. Datasets: https://www.kaggle.com/datasets/valdivinosantiago/dl-blindsr-datasets.