Adaptive Frequency Enhancement Network for Single Image Deraining

TL;DR

This paper presents AFENet, an end-to-end neural network that adaptively enhances different frequency components of images to improve single image deraining, effectively removing rain artifacts and restoring image details.

Contribution

The paper introduces a novel adaptive frequency enhancement approach with multi-scale convolutions, feature enhancement, interaction, and aggregation modules for superior deraining performance.

Findings

Outperforms existing deraining methods in both synthetic and real scenes.

Effectively removes diverse rain patterns and restores image details.

Achieves visually appealing results with improved quantitative metrics.

Abstract

Image deraining aims to improve the visibility of images damaged by rainy conditions, targeting the removal of degradation elements such as rain streaks, raindrops, and rain accumulation. While numerous single image deraining methods have shown promising results in image enhancement within the spatial domain, real-world rain degradation often causes uneven damage across an image's entire frequency spectrum, posing challenges for these methods in enhancing different frequency components. In this paper, we introduce a novel end-to-end Adaptive Frequency Enhancement Network (AFENet) specifically for single image deraining that adaptively enhances images across various frequencies. We employ convolutions of different scales to adaptively decompose image frequency bands, introduce a feature enhancement module to boost the features of different frequency components and present a novel interaction module for interchanging and merging information from various frequency branches. Simultaneously, we propose a feature aggregation module that efficiently and adaptively fuses features from different frequency bands, facilitating enhancements across the entire frequency spectrum. This approach empowers the deraining network to eliminate diverse and complex rainy patterns and to reconstruct image details accurately. Extensive experiments on both real and synthetic scenes demonstrate that our method not only achieves visually appealing enhancement results but also surpasses existing methods in performance.