Course project:
In a team, implemented the Single Image Haze Removal Using Dark Channel Prior paper. In the paper, He, Sun and Tang describe a procedure for removing haze from a single input image using the dark channel prior. The most widely used model to describe the formation of a haze image is:
I(x) = J(x)t(x) + A(1 - t(x))
where I is the observed image intensity, J is the scene radiance, A is the global atmospheric light and t is the medium transmission, describing the portion of light that reaches the camera. The goal of haze removal is to recover A, J and t from I.
The paper sets out to compute the Dark Channel Prior, estimate the Atmospheric Light A based on it, use this estimated A to estimate transmission t. This transmission is then refined using Soft Matting and the Scene Radiance J is recovered using the results.
Paper Link: http://research.microsoft.com/en-us/um/people/jiansun/papers/dehaze_cvpr2009.pdf