# A Lightweight Low-Light Image Enhancement Network via Channel Prior and Gamma Correction

arXiv: https://arxiv.org/abs/2402.18147 · HTML: https://mlsanity.com/paper/2402.18147/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 50 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 15 of 15)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction](https://mlsanity.com/paper/2205.14871/) (2022)
- [Fast End-to-End Trainable Guided Filter](https://mlsanity.com/paper/1803.05619/) (2018)
- [Dual Illumination Estimation for Robust Exposure Correction](https://mlsanity.com/paper/1910.13688/) (2019)
- [Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior](https://mlsanity.com/paper/2112.01766/) (2021)
- [A Two-stage Unsupervised Approach for Low light Image Enhancement](https://mlsanity.com/paper/2010.09316/) (2020)

## Built on by (most cited first, 6 of 6)

- [UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancement](https://mlsanity.com/paper/2512.02965/) (2025)
- [Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement](https://mlsanity.com/paper/2409.05274/) (2024)
- [EfficienT-HDR: An Efficient Transformer-Based Framework via Multi-Exposure Fusion for HDR Reconstruction](https://mlsanity.com/paper/2509.19779/) (2025)
- [Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net](https://mlsanity.com/paper/2604.11071/) (2026)
- [Retrieval-Augmented Generation-Based Color Restoration for Low-Light Image Enhancement](https://mlsanity.com/paper/2608.08211/) (2026)
- [IDM-Net: A Lightweight Illumination-Decoupled Modulation Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2609.30962/) (2026)

## Abstract (arXiv)

Human vision relies heavily on available ambient light to perceive objects. Low-light scenes pose two distinct challenges: information loss due to insufficient illumination and undesirable brightness shifts. Low-light image enhancement (LLIE) refers to image enhancement technology tailored to handle this scenario. We introduce CPGA-Net, an innovative LLIE network that combines dark/bright channel priors and gamma correction via deep learning and integrates features inspired by the Atmospheric Scattering Model and the Retinex Theory. This approach combines the use of traditional and deep learning methodologies, designed within a simple yet efficient architectural framework that focuses on essential feature extraction. The resulting CPGA-Net is a lightweight network with only 0.025 million parameters and 0.030 seconds for inference time, yet it achieves superior performance over existing LLIE methods on both objective and subjective evaluation criteria. Furthermore, we utilized knowledge distillation with explainable factors and proposed an efficient version that achieves 0.018 million parameters and 0.006 seconds for inference time. The proposed approaches inject new solution ideas into LLIE, providing practical applications in challenging low-light scenarios.