Single image dehazing via self-constructing image fusion

Abstract Haze usually degrades the visibility of outdoor images and decreases their visual quality. Previous techniques are not sufficient enough to deal with dehazing problem by using various hand-crafted priors or supervised training on paired manners. In this paper, we propose a self-constructing image fusion method for single image dehazing, which does not rely on the accuracy of global atmospheric light and transmission map. Hence, the proposed method can avoid some visual problems, such as undesirable brightness perception, unsatisfied halo artifacts and edge blur in sky regions or bright objects in dehazed images. To produce several self-constructing images with different exposures, a novel segmentation method is exploited to capture the range of global atmospheric light approximately, and a new adaptive boundary-limited L0 gradient optimization method is employed to optimize the transmission map. An adaptive selective SIFT flow multi-exposure fusion method is constructed by applying the two-layer visual sensory selector. Extensive experimental results on both synthetic and real-world images demonstrate that the proposed algorithm performs favorably against the state-of-the-art algorithms in terms of no-reference and full-reference image quality.