Low-Light Enhancement via Encoder-Decoder Network with Illumination Guidance

TL;DR

This paper presents EDNIG, a deep learning framework for low-light image enhancement that uses illumination guidance, multi-scale features, and GAN training to improve visual quality efficiently.

Contribution

The paper introduces a novel encoder-decoder network with illumination guidance and multi-scale feature extraction within a GAN framework for enhanced low-light image enhancement.

Findings

EDNIG achieves competitive quantitative and qualitative results.

The model maintains lower complexity suitable for real-world use.

Incorporating illumination guidance improves focus on underexposed regions.

Abstract

This paper introduces a novel deep learning framework for low-light image enhancement, named the Encoder-Decoder Network with Illumination Guidance (EDNIG). Building upon the U-Net architecture, EDNIG integrates an illumination map, derived from Bright Channel Prior (BCP), as a guidance input. This illumination guidance helps the network focus on underexposed regions, effectively steering the enhancement process. To further improve the model's representational power, a Spatial Pyramid Pooling (SPP) module is incorporated to extract multi-scale contextual features, enabling better handling of diverse lighting conditions. Additionally, the Swish activation function is employed to ensure smoother gradient propagation during training. EDNIG is optimized within a Generative Adversarial Network (GAN) framework using a composite loss function that combines adversarial loss, pixel-wise mean squared error (MSE), and perceptual loss. Experimental results show that EDNIG achieves competitive performance compared to state-of-the-art methods in quantitative metrics and visual quality, while maintaining lower model complexity, demonstrating its suitability for real-world applications. The source code for this work is available at https://github.com/tranleanh/ednig.