# Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs

arXiv: https://arxiv.org/abs/2006.00439 · HTML: https://mlsanity.com/paper/2006.00439/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2020.

## Built on by (most cited first, 15 of 15)

- [Low-Light Image and Video Enhancement Using Deep Learning: A Survey](https://mlsanity.com/paper/2104.10729/) (2021)
- [Seeing Motion at Nighttime with an Event Camera](https://mlsanity.com/paper/2404.11884/) (2024)
- [DMFourLLIE: Dual-Stage and Multi-Branch Fourier Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2412.00683/) (2024)
- [Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment](https://mlsanity.com/paper/2202.05972/) (2022)
- [TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2503.08168/) (2025)
- [Enlighten Anything: When Segment Anything Model Meets Low-Light Image Enhancement](https://mlsanity.com/paper/2306.10286/) (2023)
- [PromptLNet: Region-Adaptive Aesthetic Enhancement via Prompt Guidance in Low-Light Enhancement Net](https://mlsanity.com/paper/2503.08276/) (2025)
- [Joint Multi-Scale Tone Mapping and Denoising for HDR Image Enhancement](https://mlsanity.com/paper/2303.09071/) (2023)
- [Enhancement by Your Aesthetic: An Intelligible Unsupervised Personalized Enhancer for Low-Light Images](https://mlsanity.com/paper/2207.07317/) (2022)
- [Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement](https://mlsanity.com/paper/2207.07828/) (2022)
- [Enlighten-Your-Voice: When Multimodal Meets Zero-shot Low-light Image Enhancement](https://mlsanity.com/paper/2312.10109/) (2023)
- [LVRNet: Lightweight Image Restoration for Aerial Images under Low Visibility](https://mlsanity.com/paper/2301.05434/) (2023)
- [Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter](https://mlsanity.com/paper/2306.09321/) (2023)
- [DIME-Net: A Dual-Illumination Adaptive Enhancement Network Based on Retinex and Mixture-of-Experts](https://mlsanity.com/paper/2508.13921/) (2025)
- [Visibility Enhancement for Low-light Hazy Scenarios](https://mlsanity.com/paper/2308.00591/) (2023)

## Abstract (arXiv)

This paper proposes a new light-weight convolutional neural network (5k parameters) for non-uniform illumination image enhancement to handle color, exposure, contrast, noise and artifacts, etc., simultaneously and effectively. More concretely, the input image is first enhanced using Retinex model from dual different aspects (enhancing under-exposure and suppressing over-exposure), respectively. Then, these two enhanced results and the original image are fused to obtain an image with satisfactory brightness, contrast and details. Finally, the extra noise and compression artifacts are removed to get the final result. To train this network, we propose a semi-supervised retouching solution and construct a new dataset (82k images) contains various scenes and light conditions. Our model can enhance 0.5 mega-pixel (like 600*800) images in real time (50 fps), which is faster than existing enhancement methods. Extensive experiments show that our solution is fast and effective to deal with non-uniform illumination images.