Single Image Haze Removal via Joint Estimation of Detail and Transmission

Abstract

Single image haze removal is an important task in computer vision. However, haze removal is an extremely challenging problem due to it is massively ill-posed, which is that we need to estimate the transmission and the corresponding haze-free pixel from a single color measurement at each pixel. In this paper, we propose a new deep learning based method for removing haze from single input image. First, we estimate a transmission map via joint estimation of clear image details and transmission map, which is different from traditional methods which only estimating a transmission map for a hazy image. Second, we use a global regularization method to eliminate the halos and artifacts. Experimental results demonstrate that our method outperforms the other state-of-the-art dehazing methods.