# Attention-based network for low-light image enhancement

arXiv: https://arxiv.org/abs/2005.09829 · HTML: https://mlsanity.com/paper/2005.09829/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2020.

## Built on by (most cited first, 7 of 7)

- [All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation](https://mlsanity.com/paper/2308.03021/) (2023)
- [Progressive Joint Low-light Enhancement and Noise Removal for Raw Images](https://mlsanity.com/paper/2106.14844/) (2021)
- [Exploring and Evaluating Image Restoration Potential in Dynamic Scenes](https://mlsanity.com/paper/2203.11754/) (2022)
- [Attention based Broadly Self-guided Network for Low light Image Enhancement](https://mlsanity.com/paper/2112.06226/) (2021)
- [Lightweight HDR Camera ISP for Robust Perception in Dynamic Illumination Conditions via Fourier Adversarial Networks](https://mlsanity.com/paper/2204.01795/) (2022)
- [Deep dual stream residual network with contextual attention for pansharpening of remote sensing images](https://mlsanity.com/paper/2207.12004/) (2022)
- [Seeing Through the Noisy Dark: Towards Real-world Low-Light Image Enhancement and Denoising](https://mlsanity.com/paper/2210.00545/) (2022)

## Abstract (arXiv)

The captured images under low light conditions often suffer insufficient brightness and notorious noise. Hence, low-light image enhancement is a key challenging task in computer vision. A variety of methods have been proposed for this task, but these methods often failed in an extreme low-light environment and amplified the underlying noise in the input image. To address such a difficult problem, this paper presents a novel attention-based neural network to generate high-quality enhanced low-light images from the raw sensor data. Specifically, we first employ attention strategy (i.e. channel attention and spatial attention modules) to suppress undesired chromatic aberration and noise. The channel attention module guides the network to refine redundant colour features. The spatial attention module focuses on denoising by taking advantage of the non-local correlation in the image. Furthermore, we propose a new pooling layer, called inverted shuffle layer, which adaptively selects useful information from previous features. Extensive experiments demonstrate the superiority of the proposed network in terms of suppressing the chromatic aberration and noise artifacts in enhancement, especially when the low-light image has severe noise.