# Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions

arXiv: https://arxiv.org/abs/1812.00733 · HTML: https://mlsanity.com/paper/1812.00733/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2018.

## Built on by (most cited first, 18 of 18)

- [Learning A Sparse Transformer Network for Effective Image Deraining](https://mlsanity.com/paper/2303.11950/) (2023)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [Spatially-Adaptive Image Restoration using Distortion-Guided Networks](https://mlsanity.com/paper/2108.08617/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks](https://mlsanity.com/paper/2303.15710/) (2023)
- [Bringing Old Films Back to Life](https://mlsanity.com/paper/2203.17276/) (2022)
- [Pik-Fix: Restoring and Colorizing Old Photos](https://mlsanity.com/paper/2205.01902/) (2022)
- [Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network](https://mlsanity.com/paper/2009.14563/) (2020)
- [Operation-wise Attention Network for Tampering Localization Fusion](https://mlsanity.com/paper/2105.05515/) (2021)
- [A Close Look at Few-shot Real Image Super-resolution from the Distortion Relation Perspective](https://mlsanity.com/paper/2111.13078/) (2021)
- [Kernelized Back-Projection Networks for Blind Super Resolution](https://mlsanity.com/paper/2302.08478/) (2023)
- [AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark](https://mlsanity.com/paper/2607.02131/) (2026)
- [Super-Resolving Compressed Video in Coding Chain](https://mlsanity.com/paper/2103.14247/) (2021)
- [ROMNet: Renovate the Old Memories](https://mlsanity.com/paper/2202.02606/) (2022)
- [Rethinking Generative Methods for Image Restoration in Physics-based Vision: A Theoretical Analysis from the Perspective of Information](https://mlsanity.com/paper/2212.02198/) (2022)
- [A Unified Detection Pipeline for Robust Object Detection in Fisheye-Based Traffic Surveillance](https://mlsanity.com/paper/2510.20016/) (2025)
- [Learning to Restore Multi-Degraded Images via Ingredient Decoupling and Task-Aware Path Adaptation](https://mlsanity.com/paper/2511.04920/) (2025)
- [Physically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolution](https://mlsanity.com/paper/2511.10166/) (2025)

## Abstract (arXiv)

Many studies have been conducted so far on image restoration, the problem of restoring a clean image from its distorted version. There are many different types of distortion which affect image quality. Previous studies have focused on single types of distortion, proposing methods for removing them. However, image quality degrades due to multiple factors in the real world. Thus, depending on applications, e.g., vision for autonomous cars or surveillance cameras, we need to be able to deal with multiple combined distortions with unknown mixture ratios. For this purpose, we propose a simple yet effective layer architecture of neural networks. It performs multiple operations in parallel, which are weighted by an attention mechanism to enable selection of proper operations depending on the input. The layer can be stacked to form a deep network, which is differentiable and thus can be trained in an end-to-end fashion by gradient descent. The experimental results show that the proposed method works better than previous methods by a good margin on tasks of restoring images with multiple combined distortions.