Temporal Rain Decomposition With Spatial Structure Guidance For Video Deraining

Recently, removing rain streaks from videos has drawn wide concerns in vision and multimedia communities. Most existing approaches for video deraining always generate unsatisfactory performance, e.g., imperfect removal effects and important detail loss. The cause of these issues lies in the description of rain streaks and the underutilization of spatial/temporal information. In this work, we propose a multiframe deraining network with temporal rain decomposition and spatial structure guidance to more effectively accomplish video deraining. A learnable decomposition method is defined to learn the distribution of rain, where the location map acts on a single-frame deraining block. We construct a multi-frame fusion module with a detailed guidance map to integrate temporal and spatial information. Many evaluated experiments demonstrate that our algorithm performs favorably on video deraining tasks compared with other methods. The elaborate ablation study in terms of network architecture fully indicates the effectiveness of our network.