Single Image Dehazing Using Bounded Channel Difference Prior

The single image dehazing task has made significant progress recently, aiming to recover the contrast and color of the scattered image. Many patch prior based dehazing methods have been explored, and this paper proposes another single image dehazing method by analyzing the prior information of local dehazed patches. With our observation, when the estimated transmission value varies from the ground-truth transmission value to 1, the output value of a metric function decrease correspondingly, which is defined based on the difference maps among three RGB channels of local dehazed patches normalized using global atmospheric light. Under additional bounding, the local transmission value can be estimated accurately. To reduce computation time, the whole image is divided into many small patches, and within each patch, we estimate a transmission value accurately. We further use weighted interpolation and guided filtering to refine the edges and details of the rough transmission map. Finally, we evaluate the proposed method using Fattal’s synthetic haze images, SOTS dataset, and a wide variety of real-world haze images. Experiments show that our method outperforms other state-of-the-art dehazing algorithms by a large margin, especially on synthetic noisy haze images.