Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior

Rain is a common natural phenomenon. Taking images in the rain however often results in degraded quality of images, thus compromises the performance of many computer vision systems. Most existing de-rain algorithms use only one single input image and aim to recover a clean image. Few work has exploi...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International journal of computer vision Ročník 130; číslo 7; s. 1754 - 1769
Hlavní autori: Zhang, Kaihao, Luo, Wenhan, Yu, Yanjiang, Ren, Wenqi, Zhao, Fang, Li, Changsheng, Ma, Lin, Liu, Wei, Li, Hongdong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.07.2022
Springer
Springer Nature B.V
Predmet:
Algorithms
Artificial Intelligence
Computer Imaging
Computer Science
Computer vision
Datasets
Feature extraction
Image Processing and Computer Vision
Image quality
Image segmentation
Machine vision
Pattern Recognition
Pattern Recognition and Graphics
Rain
Semantic segmentation
Semantics
Vision
Vision systems
Deep learning
Parallel stereo network
Stereo image deraining
View fusion
ISSN:0920-5691, 1573-1405
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Rain is a common natural phenomenon. Taking images in the rain however often results in degraded quality of images, thus compromises the performance of many computer vision systems. Most existing de-rain algorithms use only one single input image and aim to recover a clean image. Few work has exploited stereo images. Moreover, even for single image based monocular deraining, many current methods fail to complete the task satisfactorily because they mostly rely on per pixel loss functions and ignore semantic information. In this paper, we present a Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information. Specifically, we develop a Semantic-Aware Deraining Module (SADM) which solves both tasks of semantic segmentation and deraining of scenes, and a Semantic-Fusion Network (SFNet) and a View-Fusion Network (VFNet) which fuse semantic information and multi-view information respectively. In addition, we also introduce an Enhanced Paired Rain Removal Network (EPRRNet) which exploits semantic prior to remove rain streaks from stereo images. We first use a coarse deraining network to reduce the rain streaks on the input images, and then adopt a pre-trained semantic segmentation network to extract semantic features from the coarse derained image. Finally, a parallel stereo deraining network fuses semantic and multi-view information to restore finer results. We also propose new stereo based rainy datasets for benchmarking. Experiments on both monocular and the newly proposed stereo rainy datasets demonstrate that the proposed method achieves the state-of-the-art performance. https://github.com/HDCVLab/Stereo-Image-Deraining .
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-022-01620-w