A fast dark channel prior-based depth map approximation method for dehazing single images

Images of outdoor scenes lose visiblity and contrast due to the presence of atmospheric haze, fog and smoke. The recently proposed dark channel prior-based approach appears to be the most successful solution and produces the best result in most cases. However, this approach suffers from a complex depth map refinement process, which consumes much computational time. In this paper, we propose a novel fast depth map approximation method using the dark channel prior. This approximation makes use of the pixel-wise depth map and the observation that most dehazing artifacts occur in the area in which the original estimated depth map has large difference from its pixel-wise depth map. For fast implementation, we simply replace these edge area depth information by the newly estimated depth information. Experiments show that comparing with the original dark channel approach, the proposed new method has a speedup gain of about 50 or more while at the same time produces similar or better results.