Multi-Scale Hourglass Hierarchical Fusion Network for Single Image Deraining
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 872-879
Abstract
Rain streaks bring serious blurring and visual quality degradation, which often vary in size, direction and density. Current CNN-based methods achieve encouraging performance, while are limited to depict rain characteristics and recover image details in the poor visibility environment. To address these issues, we present a Multi-scale Hourglass Hierarchical Fusion Network (MH 2 F-Net) in end-to-end manner, to exactly captures rain streak features with multi-scale extraction, hierarchical distillation and information aggregation. For better extracting the features, a novel Multi-scale Hourglass Extraction Block (MHEB) is proposed to get local and global features across different scales through down- and up-sample process. Besides, a Hierarchical Attentive Distillation Block (HADB) then employs the dual attention feature responses to adaptively recalibrate the hierarchical features and eliminate the redundant ones. Further, we introduce a Residual Projected Feature Fusion (RPFF) strategy to progressively discriminate feature learning and aggregate different features instead of directly concatenating or adding. Extensive experiments on both synthetic and real rainy datasets demonstrate the effectiveness of the designed MH 2 F-Net by comparing with recent state-of-the-art deraining algorithms. Our source code will be available on the GitHub: https://github.com/cxtalk/MH2F-Net.Keywords
This publication has 11 references indexed in Scilit:
- Single Image Deraining: From Model-Based to Data-Driven and BeyondIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Single Image Deraining via Recurrent Hierarchy Enhancement Network2019
- Image De-Raining Using a Conditional Generative Adversarial NetworkIEEE Transactions on Circuits and Systems for Video Technology, 2019
- Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset2019
- Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining2018
- Removing Rain from Single Images via a Deep Detail Network2017
- Clearing the Skies: A Deep Network Architecture for Single-Image Rain RemovalIEEE Transactions on Image Processing, 2017
- Loss Functions for Image Restoration With Neural NetworksIEEE Transactions on Computational Imaging, 2016
- Automatic Single-Image-Based Rain Streaks Removal via Image DecompositionIEEE Transactions on Image Processing, 2011
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004