Image dehazing using regularized optimization

摘要: The presence of haze shifts the color and degrades visibility outdoor scenes in digital images. In this paper, we propose a novel effective optimization algorithm for single image dehazing. We first formulate dehazing model into linear convex problem, develop its cost function based on two basic observations: first, hazy exhibits low contrast general; second, distance-map from scene to camera, is piecewise smooth. Then, implement specific our problem using Split Bregman iteration. experimental results show that proposed not only enhances but also preserves details sharp edges. Our demonstrate effectiveness