LAUSR

Abstract A variety of empirical methods, which are represented by dark channel prior, have been proved effective for haze removal. However, undesirable artifacts and color distortion are still left on some of dehazing results, which directly determines the performance of computer vision tasks. Different from traditional statistical methods, we apply Multi-dimensional theory that quickly predicts haze free images. To this purpose, the local manifold similarity is employed to reduce the error of initial estimation. Moreover, contrast-based Gaussian curvature is also introduced in order to obtain the smoothness transmission map. Compared with conventional methods, quantitative and qualitative comparisons have shown our approach improvement visual results.