A faithful restoration of haze images using an optimized transmission map
Elisee A Kponou, Zhengning Wang, Ping Wei, Yan Jiang, Xiaolong Ni, Mamadou Hady Bah · 2014
Nowadays, image enhancement, image restoration and dehazing had made a great progress. This paper addresses the problem of dehazing which is a serious question in computer vision and consumer photography applications. Due to the weakness of the existing methods to compute an accurate transmission map, we use the binocular vision method to compute the depth map. We have used in this paper, the discrepancy between the left and right image to compute the transmission map which renders our algorithms much faster and more accurately. Extensive experimental results show that our new approach can obtain excellent performance of visual quality. The lower computation time and the simplicity of our design over other state-of-the-art methods allow it to be used in real-time application.