Single Image Deraining via Scale-space Invariant Attention Neural Network

TL;DR

This paper introduces a novel scale-space invariant attention neural network for single image deraining, leveraging multi-scale correlation in feature space and an attention mechanism to enhance rain artifact removal.

Contribution

The paper proposes a new multi-scale representation using scale-space theory and a scale-invariant attention mechanism to improve deraining performance.

Findings

Outperforms state-of-the-art deraining methods on synthetic datasets.

Effective in real rainy scenes with diverse rain patterns.

Enhances visual clarity and detail preservation.

Abstract

Image enhancement from degradation of rainy artifacts plays a critical role in outdoor visual computing systems. In this paper, we tackle the notion of scale that deals with visual changes in appearance of rain steaks with respect to the camera. Specifically, we revisit multi-scale representation by scale-space theory, and propose to represent the multi-scale correlation in convolutional feature domain, which is more compact and robust than that in pixel domain. Moreover, to improve the modeling ability of the network, we do not treat the extracted multi-scale features equally, but design a novel scale-space invariant attention mechanism to help the network focus on parts of the features. In this way, we summarize the most activated presence of feature maps as the salient features. Extensive experiments results on synthetic and real rainy scenes demonstrate the superior performance of our scheme over the state-of-the-arts.