Depth and Reflection Total Variation for Single Image Dehazing
This addresses the ill-posed problem of haze removal for computer vision applications, but it is incremental as it builds on existing models and assumptions.
The paper tackles single image dehazing by combining a haze formation model with Retinex theory, assuming piecewise smooth depth and reflection functions regularized with total variation, and demonstrates effective restoration of vivid and contrastive images.
Haze removal has been a very challenging problem due to its ill-posedness, which is more ill-posed if the input data is only a single hazy image. In this paper, we present a new approach for removing haze from a single input image. The proposed method combines the model widely used to describe the formation of a haze image with the assumption in Retinex that an image is the product of the illumination and the reflection. We assume that the depth and reflection functions are spatially piecewise smooth in the model, where the total variation is used for the regularization. The proposed model is defined as a constrained optimization problem, which is solved by an alternating minimization scheme and the fast gradient projection algorithm. Some theoretic analyses are given for the proposed model and algorithm. Finally, numerical examples are presented to demonstrate that our method can restore vivid and contrastive hazy images effectively.