UM  > Faculty of Science and Technology
Residential Collegefalse
Status已發表Published
Multi-stage Curvature-guided Network for Progressive Single Image Reflection Removal
Song, Binbin; Zhou, Jiantao; Wu, Haiwei
2022
Source PublicationIEEE Transactions on Circuits and Systems for Video Technology
ISSN1051-8215
Volume32Issue:10Pages:6515-6529
Abstract

Thanks to the powerful learning capability, deep neural networks (DNNs) have acquired broad applications in single image reflection removal. The DNN-based algorithms relax the constraints of specific priors and learn to generate visually pleasant background layers from massive training data. However, most of them employ a single network structure to recover both the semantic information and local details of the background, which may lead to obvious reflection residue or even failure. To mitigate this deficiency, in this work, we propose a Multi-stage Curvature-guided De-Reflection Network (MCDRNet), which combines multiple network architectures in a unified framework to progressively reconstruct the background layer and refine the fine-grained details. Our framework consists of three stages, where the encoder-decoders are exploited in the first two stages to recover the semantic components of background layers with lower scales and a variant ResNet is applied in the last stage to refine the background details with the original input resolution. In the first two stages, to introduce the structural guidance for the reflection removal, we cascade another decoder branch to restore the curvature map of the background. In addition, at the end of the first two stages, instead of directly passing the intermediate estimates to the next stage, we propose a Non-local Attention Module (NAM) to augment and transmit the features from decoders. Extensive experimental results on several public datasets demonstrate that the proposed MCDRNet outperforms the state-of-the-art methods quantitatively and generates visually better reflection removal results. The source code and pre-trained models are available at https://github.com/NamecantbeNULL/MCDRNet.

KeywordCurvature Guidance Decoding Feature Extraction Image Restoration Multi-stage Network Network Architecture Non-local Attention Semantics Single Image Reflection Removal Training Training Data
DOI10.1109/TCSVT.2022.3168828
URLView the original
Indexed BySCIE
Language英語English
WOS Research AreaEngineering
WOS SubjectEngineering, Electrical & Electronic
WOS IDWOS:000864197600006
Scopus ID2-s2.0-85128607628
Fulltext Access
Citation statistics
Cited Times [WOS]:1   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionFaculty of Science and Technology
AffiliationState Key Laboratory of Internet of Things for Smart City, and Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau 999078, China
First Author AffilicationFaculty of Science and Technology
Recommended Citation
GB/T 7714
Song, Binbin,Zhou, Jiantao,Wu, Haiwei. Multi-stage Curvature-guided Network for Progressive Single Image Reflection Removal[J]. IEEE Transactions on Circuits and Systems for Video Technology,2022,32(10):6515-6529.
APA Song, Binbin,Zhou, Jiantao,&Wu, Haiwei.(2022).Multi-stage Curvature-guided Network for Progressive Single Image Reflection Removal.IEEE Transactions on Circuits and Systems for Video Technology,32(10),6515-6529.
MLA Song, Binbin,et al."Multi-stage Curvature-guided Network for Progressive Single Image Reflection Removal".IEEE Transactions on Circuits and Systems for Video Technology 32.10(2022):6515-6529.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Song, Binbin]'s Articles
[Zhou, Jiantao]'s Articles
[Wu, Haiwei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Song, Binbin]'s Articles
[Zhou, Jiantao]'s Articles
[Wu, Haiwei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Song, Binbin]'s Articles
[Zhou, Jiantao]'s Articles
[Wu, Haiwei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.