《Single Image Haze Removal Using Dark Channel Prior_cvpr2016》.pdf

Single Image Haze Removal Using Dark Channel Prior Kaiming He1 Jian Sun2 Xiaoou Tang1,2 1The Chinese University of Hong Kong 2Microsoft Research Asia Abstract In this paper, we propose a simple but effective image prior - dark channel prior to remove haze from a sin- gle input image. The dark channel prior is a kind of statis- tics of the haze-free outdoor images. It is based on a key observation - most local patches in haze-free outdoor im- ages contain some pixels which have very low intensities in at least one color channel. Using this prior with the haze imaging model, we can directly estimate the thickness of the haze and recover a high quality haze-free image. Results on a variety of outdoor haze images demonstrate the power of the proposed prior. Moreover, a high quality depth map can also be obtained as a by-product of haze removal. Figure 1. Haze removal using a single image. (a) input haze image. (b) image after haze removal by our approach. (c) our recovered 1. Introduction depth map. Images of outdoor scenes are usually degraded by the turbid medium (e.g., particles, water-droplets) in the atmo- contrast scene radiance. Last, the haze removal can produce sphere. Haze, fog, and smoke are such phenomena due depth information and benefit many vision algorithms and to atmospheric absorption and scattering. The irradiance advanced image editing. Haze or fog can be a useful depth received by the camera from the scene point is attenuated clue for scene understanding. The bad haze image can be along the line of sight. Furtherm