A Training-Free Adaptive Low-Light Image Enhancement Framework via Decoupled HSV Optimization and Dual-IQA Guidance
This study introduces a training-free, self-contained adaptive low-light image enhancement (LLIE) framework driven by a metaheuristic optimization algorithm (MOA) and a context-aware dual image quality assessment (IQA) engine. Although deep-learning-based methods exhibit rapid inference, their static parameters often s...