Variational Low-light Image Enhancement based on a Haze Model
Joongchol Shin, Hasil Park, Jinho Park, Joonki Paik, Jinsol Ha · IEIE Transactions on Smart Processing and Computing · 2018
Under low-illumination conditions, an acquired image is degraded by a limited dynamic range and noise in signal amplification. To solve this problem, we propose a haze model-based variational low-light image-enhancement method. The proposed method includes two steps: i) estimation of the initial transmission map using block-based dark channel prior and a Gaussian pyramid, and ii) L2-norm regularized optimization based on the haze model. Experimental results show that the proposed enhancement method outperforms conventional state-of-the-art methods in terms of visible contrast without noise amplification.