# Deep learning architectural designs for super-resolution of noisy images

arXiv: https://arxiv.org/abs/2102.05105 · HTML: https://mlsanity.com/paper/2102.05105/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 9 Feb 2021.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- [The Little Engine that Could: Regularization by Denoising (RED)](https://mlsanity.com/paper/1611.02862/) (2016)
- [Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applications](https://mlsanity.com/paper/1605.01710/) (2016)
- [Wide Activation for Efficient and Accurate Image Super-Resolution](https://mlsanity.com/paper/1808.08718/) (2018)
- [Super-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning](https://mlsanity.com/paper/1811.12866/) (2018)
- [New Techniques for Preserving Global Structure and Denoising with Low Information Loss in Single-Image Super-Resolution](https://mlsanity.com/paper/1805.03383/) (2018)
- [Adaptive Quantile Sparse Image (AQuaSI) Prior for Inverse Imaging Problems](https://mlsanity.com/paper/1804.02152/) (2018)

## Built on by (most cited first, 5 of 5)

- [LIT-Former: Linking In-plane and Through-plane Transformers for Simultaneous CT Image Denoising and Deblurring](https://mlsanity.com/paper/2302.10630/) (2023)
- [Unsupervised Image Decomposition with Phase-Correlation Networks](https://mlsanity.com/paper/2110.03473/) (2021)
- [Benchmarking Probabilistic Deep Learning Methods for License Plate Recognition](https://mlsanity.com/paper/2302.01427/) (2023)
- [Collaboratively Learning Federated Models from Noisy Decentralized Data](https://mlsanity.com/paper/2409.02189/) (2024)
- [Learning-Based and Quality Preserving Super-Resolution of Noisy Images](https://mlsanity.com/paper/2311.02254/) (2023)

## Abstract (arXiv)

Recent advances in deep learning have led to significant improvements in single image super-resolution (SR) research. However, due to the amplification of noise during the upsampling steps, state-of-the-art methods often fail at reconstructing high-resolution images from noisy versions of their low-resolution counterparts. However, this is especially important for images from unknown cameras with unseen types of image degradation. In this work, we propose to jointly perform denoising and super-resolution. To this end, we investigate two architectural designs: "in-network" combines both tasks at feature level, while "pre-network" first performs denoising and then super-resolution. Our experiments show that both variants have specific advantages: The in-network design obtains the strongest results when the type of image corruption is aligned in the training and testing dataset, for any choice of denoiser. The pre-network design exhibits superior performance on unseen types of image corruption, which is a pathological failure case of existing super-resolution models. We hope that these findings help to enable super-resolution also in less constrained scenarios where source camera or imaging conditions are not well controlled. Source code and pretrained models are available at https://github.com/ angelvillar96/super-resolution-noisy-images.