Deep Feature Interactive Aggregation Network for Single Image Deraining

Abstract

Single image deraining aims to remove rain streaks from a degraded input and reconstruct a high-quality image. In recent years, image processing tasks mostly applied a U-shaped architecture to capture rich contextual information. However, it is difficult to achieve long-range pixel dependencies because of the local receptive field of the convolution operation. In this paper, we propose a deep feature interactive aggregation network for single image deraining to enhance long-range dependencies among features and realize the interaction of information. To fully utilize high-level semantic features, we design a long-range dependency feature aggregation module to significantly improve the representational ability of the original U-shaped architecture. It aggregates multi-scale features and calculates the interactive attention of non-overlapping patches among feature maps. In addition, we adopt group normalization to retain the independence of each given image. It interacts with the information among features in an individual image and normalizes the channels of each group to weaken the correlation between batch data processing. Experimental results on widely acknowledged datasets also demonstrate the superiority of our proposed network over previous state-of-the-art methods.