Multi-scale Features Fusion Network for Single Image Deraining

Single image rain removal is an important research direction in the field of computer vision. In this paper, the Multi-scale Features Fusion Network (MFFN) is presented for rain removal. MFFN is mainly composed of Multi-features Fusion Module (MFM) and Dual Attention Module (DAM). In the MFM, we mak...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC) Vol. 10; pp. 615 - 619
Main Authors Lai, Yanming, Li, Qishen, Huang, Hua, Li, Qiufeng
Format Conference Proceeding
LanguageEnglish
Published IEEE 17.06.2022
Subjects
attention mechanism
Computer vision
Conferences
Dams
Data mining
Deep learning
Feature extraction
MFFN
Rain
single image rain removal
Online AccessGet full text

Cover

More Information
Summary:Single image rain removal is an important research direction in the field of computer vision. In this paper, the Multi-scale Features Fusion Network (MFFN) is presented for rain removal. MFFN is mainly composed of Multi-features Fusion Module (MFM) and Dual Attention Module (DAM). In the MFM, we make the improved dense block and the dilation convolutions to form the feature extraction branches, which is conducive to improve the receptive fields of network. Subsequently, the bottom-up connection method is adopted between branches to help different branches make full use of image information. Then, feature branches are merged to fusion different features. DAM is consisted of purposed SA Block and standard SE Block. The purpose of DAM is to reduce the non-rain features which is extracted by the network. Experiments show that MFFN can obtain the better result of rain removal than several advanced methods.
ISSN:2693-2865
DOI:10.1109/ITAIC54216.2022.9836884