Residual Squeeze-and-Excitation Network for Fast Image Deraining

TL;DR

This paper introduces RSEN, a lightweight residual squeeze-and-excitation network that efficiently removes rain streaks from images, outperforming existing methods in both speed and quality.

Contribution

The paper presents a novel residual squeeze-and-excitation block within a lightweight encoder-decoder architecture for fast and effective image deraining.

Findings

Reduces computational complexity significantly

Improves deraining performance over state-of-the-art methods

Operates in a single stage for efficiency

Abstract

Image deraining is an important image processing task as rain streaks not only severely degrade the visual quality of images but also significantly affect the performance of high-level vision tasks. Traditional methods progressively remove rain streaks via different recurrent neural networks. However, these methods fail to yield plausible rain-free images in an efficient manner. In this paper, we propose a residual squeeze-and-excitation network called RSEN for fast image deraining as well as superior deraining performance compared with state-of-the-art approaches. Specifically, RSEN adopts a lightweight encoder-decoder architecture to conduct rain removal in one stage. Besides, both encoder and decoder adopt a novel residual squeeze-and-excitation block as the core of feature extraction, which contains a residual block for producing hierarchical features, followed by a squeeze-and-excitation block for channel-wisely enhancing the resulted hierarchical features. Experimental results demonstrate that our method can not only considerably reduce the computational complexity but also significantly improve the deraining performance compared with state-of-the-art methods.