<p>Enhancing images captured in low-light environments requires increasing brightness while preserving fine details and reducing noise. Many existing enhancement models have attempted to address this issue; however, they often fail under complex lighting conditions, leading to either over-enhancement, which causes loss of natural appearance, or under-enhancement, which leaves the image poorly illuminated. A common drawback of these models is their dependence on fixed enhancement parameters, making them inflexible in adapting to diverse brightness levels and scene content across various images. To overcome these limitations, this paper proposes a novel low-light image enhancement model that leverages an adaptive enhancement matrix. The core of the model lies in its adaptive adjustment module, which dynamically fine-tunes enhancement weights based on the unique features of each image. This adaptive strategy enables the model to effectively handle a wide range of lighting conditions and image types. As a result, it can enhance images more naturally and consistently compared to static-parameter methods. Comprehensive experimental evaluations on standard benchmark datasets show that the proposed model delivers significant improvements over existing techniques. It excels in both qualitative aspects—such as visual clarity and naturalness—and quantitative metrics like PSNR, FOM and SSIM, proving its robustness and versatility in real-world applications.</p>