# Improving Super-Resolution Performance using Meta-Attention Layers

arXiv: https://arxiv.org/abs/2110.14638 · HTML: https://mlsanity.com/paper/2110.14638/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 27 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [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)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Deep Learning for Image Super-resolution: A Survey](https://mlsanity.com/paper/1902.06068/) (2019)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [Deep Unfolding Network for Image Super-Resolution](https://mlsanity.com/paper/2003.10428/) (2020)
- [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)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [A Deep Journey into Super-resolution: A survey](https://mlsanity.com/paper/1904.07523/) (2019)
- [NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2005.01996/) (2020)
- [Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations](https://mlsanity.com/paper/2004.06965/) (2020)
- [Learning Spatial Attention for Face Super-Resolution](https://mlsanity.com/paper/2012.01211/) (2020)
- [Facial Attribute Capsules for Noise Face Super Resolution](https://mlsanity.com/paper/2002.06518/) (2020)

## Built on by (most cited first, 2 of 2)

- [The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks](https://mlsanity.com/paper/2211.05018/) (2022)
- [PTSR: Patch Translator for Image Super-Resolution](https://mlsanity.com/paper/2310.13216/) (2023)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have achieved impressive results across many super-resolution (SR) and image restoration tasks. While many such networks can upscale low-resolution (LR) images using just the raw pixel-level information, the ill-posed nature of SR can make it difficult to accurately super-resolve an image which has undergone multiple different degradations. Additional information (metadata) describing the degradation process (such as the blur kernel applied, compression level, etc.) can guide networks to super-resolve LR images with higher fidelity to the original source. Previous attempts at informing SR networks with degradation parameters have indeed been able to improve performance in a number of scenarios. However, due to the fully-convolutional nature of many SR networks, most of these metadata fusion methods either require a complete architectural change, or necessitate the addition of significant extra complexity. Thus, these approaches are difficult to introduce into arbitrary SR networks without considerable design alterations. In this paper, we introduce meta-attention, a simple mechanism which allows any SR CNN to exploit the information available in relevant degradation parameters. The mechanism functions by translating the metadata into a channel attention vector, which in turn selectively modulates the network's feature maps. Incorporating meta-attention into SR networks is straightforward, as it requires no specific type of architecture to function correctly. Extensive testing has shown that meta-attention can consistently improve the pixel-level accuracy of state-of-the-art (SOTA) networks when provided with relevant degradation metadata. For PSNR, the gain on blurred/downsampled (X4) images is of 0.2969 dB (on average) and 0.3320 dB for SOTA general and face SR models, respectively.