Abstract
Low-light image enhancement is a challenging problem in computer vision and image processing, crucial for applications such as surveillance, autonomous driving, and medical imaging. Traditional image enhancement techniques often struggle with noise amplification and loss of detail under poor lighting. This paper reviews recent advances in AI-driven signal processing methods, focusing on deep learning architectures and hybrid techniques designed to improve image quality in low-light conditions. We discuss state-of-the-art convolutional neural networks (CNNs), generative adversarial networks (GANs), and transformer-based models. Additionally, the integration of signal processing principles with AI frameworks is highlighted, emphasizing noise reduction, detail restoration, and color correction. Experimental results demonstrate superior performance compared to classical methods, suggesting that AI-driven approaches represent a promising direction for robust low-light image enhancement.

This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2021 Dr. Maria Jensen (Author)