RoDeRain: Rotational Video Derain via Nonconvex and Nonsmooth Optimization

Abstract

Video derain is an important issue in the field of digital image processing and computer vision. This paper divides rain streaks into two types: one is rain in natural scenes, and the other is rain in stochastic scenes. In this paper, we propose a novel rotational video derain algorithm via nonconvex and nonsmooth algorithm (RoDerain). Not only can the rain streaks in natural scene be removed, but the rain streaks in stochastic scene can be also well removed. This paper added the rotation operator based on the discriminatively intrinsic priors of rain streaks and clean videos to remove the rain streaks in both natural and stochastic scenes.For the low rank problem of the background, we replace the solution of the nuclear norm with improved IRNN-Capped L1 suitable for tensor. Finally,this paper used the Alternating Direction Method of Multipliers (ADMM) to optimize the solution of the proposed rain streaks removal algorithm model.The disadvantage is that global information is not considered. And the extensive experiment results show that our proposed algorithm performs favorably in comparison to several popular rain removal algorithms.