Multi-Scale Features Joint Rain Removal For Single Image

Abstract

The presence of rain and haze often cause degradation of images. Therefore, it is important to remove rain or haze and recover the background in outdoor vision systems. Due to the limited size of the network acceptance domain, the pixel value of each spatial position can only be inferred from the surrounding small local area; thus, it is often difficult to remove long rain streaks using existing methods. Therefore, we propose a feature joint dense network (FJDN) to extract multi-scale aggregation features. First, we design a multiscale feature extraction module that uses four dilated convolutional layers to extract multi-scale features. These multi-scale features are then combined into one feature map. We also aggregate three multi-scale features in feature joint dense block (FJDB). By using multi-scale features, we can effectively detect rain streaks of different lengths. Finally, we perform multiple experiments to visually and quantitatively compare our method with several existing methods, demonstrating its superiority. The proposed method is also applied to image dehazing.