Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386484453> ?p ?o ?g. }
- W4386484453 endingPage "104814" @default.
- W4386484453 startingPage "104814" @default.
- W4386484453 abstract "Existing deep learning based methods have shown their advantages in multi-focus image fusion task. However, most methods still suffer from inaccurate focus region detection. In this paper, we employ the property of part-whole relationships embedded by the Capsule Network (CapsNet) to solve the problem. Specifically, we introduce CapsNet in multi-focus image fusion task, and design a structure-guided flow module, which fully utilizes structure information to help locate focus regions. CapsNet is introduced to extract structure features by supervising gradient information of the image. Compared with traditional convolutional neural networks (CNNs), CapsNet takes into account the correlation of features from different positions, such that it encodes more compact features. Once structure features are obtained, a flow alignment module is introduced to learn flow field between structure and image features, and propagate effectively structure features to image features to make confident focus region detection. Experimental results show the proposed method achieves robust fusion performance on three publicly available multi-focus datasets, and outperforms or is comparable to the state-of-the-art methods." @default.
- W4386484453 created "2023-09-07" @default.
- W4386484453 creator A5014932626 @default.
- W4386484453 creator A5015214891 @default.
- W4386484453 creator A5039153796 @default.
- W4386484453 date "2023-10-01" @default.
- W4386484453 modified "2023-09-30" @default.
- W4386484453 title "Multi-focus image fusion using structure-guided flow" @default.
- W4386484453 cites W1994616697 @default.
- W4386484453 cites W1994877111 @default.
- W4386484453 cites W1999034606 @default.
- W4386484453 cites W2020442368 @default.
- W4386484453 cites W2025133197 @default.
- W4386484453 cites W2026651590 @default.
- W4386484453 cites W2034995331 @default.
- W4386484453 cites W2039465985 @default.
- W4386484453 cites W2048661006 @default.
- W4386484453 cites W2054273865 @default.
- W4386484453 cites W2057769475 @default.
- W4386484453 cites W2064562647 @default.
- W4386484453 cites W2091484864 @default.
- W4386484453 cites W2116702374 @default.
- W4386484453 cites W2532801510 @default.
- W4386484453 cites W2559870345 @default.
- W4386484453 cites W2794731943 @default.
- W4386484453 cites W2901572775 @default.
- W4386484453 cites W2912126472 @default.
- W4386484453 cites W2941380944 @default.
- W4386484453 cites W2961850738 @default.
- W4386484453 cites W2982243647 @default.
- W4386484453 cites W2998012573 @default.
- W4386484453 cites W3010335025 @default.
- W4386484453 cites W3047443805 @default.
- W4386484453 cites W3081131687 @default.
- W4386484453 cites W3083574456 @default.
- W4386484453 cites W3095064240 @default.
- W4386484453 cites W3134036581 @default.
- W4386484453 cites W3135530979 @default.
- W4386484453 cites W4308979724 @default.
- W4386484453 cites W4312617484 @default.
- W4386484453 cites W4377091052 @default.
- W4386484453 cites W4386634500 @default.
- W4386484453 doi "https://doi.org/10.1016/j.imavis.2023.104814" @default.
- W4386484453 hasPublicationYear "2023" @default.
- W4386484453 type Work @default.
- W4386484453 citedByCount "0" @default.
- W4386484453 crossrefType "journal-article" @default.
- W4386484453 hasAuthorship W4386484453A5014932626 @default.
- W4386484453 hasAuthorship W4386484453A5015214891 @default.
- W4386484453 hasAuthorship W4386484453A5039153796 @default.
- W4386484453 hasConcept C108583219 @default.
- W4386484453 hasConcept C111472728 @default.
- W4386484453 hasConcept C115961682 @default.
- W4386484453 hasConcept C120665830 @default.
- W4386484453 hasConcept C121332964 @default.
- W4386484453 hasConcept C127413603 @default.
- W4386484453 hasConcept C138885662 @default.
- W4386484453 hasConcept C153180895 @default.
- W4386484453 hasConcept C154945302 @default.
- W4386484453 hasConcept C189950617 @default.
- W4386484453 hasConcept C192209626 @default.
- W4386484453 hasConcept C201995342 @default.
- W4386484453 hasConcept C202444582 @default.
- W4386484453 hasConcept C2780451532 @default.
- W4386484453 hasConcept C31972630 @default.
- W4386484453 hasConcept C33923547 @default.
- W4386484453 hasConcept C41008148 @default.
- W4386484453 hasConcept C52622490 @default.
- W4386484453 hasConcept C69744172 @default.
- W4386484453 hasConcept C81363708 @default.
- W4386484453 hasConcept C9652623 @default.
- W4386484453 hasConceptScore W4386484453C108583219 @default.
- W4386484453 hasConceptScore W4386484453C111472728 @default.
- W4386484453 hasConceptScore W4386484453C115961682 @default.
- W4386484453 hasConceptScore W4386484453C120665830 @default.
- W4386484453 hasConceptScore W4386484453C121332964 @default.
- W4386484453 hasConceptScore W4386484453C127413603 @default.
- W4386484453 hasConceptScore W4386484453C138885662 @default.
- W4386484453 hasConceptScore W4386484453C153180895 @default.
- W4386484453 hasConceptScore W4386484453C154945302 @default.
- W4386484453 hasConceptScore W4386484453C189950617 @default.
- W4386484453 hasConceptScore W4386484453C192209626 @default.
- W4386484453 hasConceptScore W4386484453C201995342 @default.
- W4386484453 hasConceptScore W4386484453C202444582 @default.
- W4386484453 hasConceptScore W4386484453C2780451532 @default.
- W4386484453 hasConceptScore W4386484453C31972630 @default.
- W4386484453 hasConceptScore W4386484453C33923547 @default.
- W4386484453 hasConceptScore W4386484453C41008148 @default.
- W4386484453 hasConceptScore W4386484453C52622490 @default.
- W4386484453 hasConceptScore W4386484453C69744172 @default.
- W4386484453 hasConceptScore W4386484453C81363708 @default.
- W4386484453 hasConceptScore W4386484453C9652623 @default.
- W4386484453 hasFunder F4320321001 @default.
- W4386484453 hasLocation W43864844531 @default.
- W4386484453 hasOpenAccess W4386484453 @default.
- W4386484453 hasPrimaryLocation W43864844531 @default.
- W4386484453 hasRelatedWork W2279398222 @default.
- W4386484453 hasRelatedWork W2731899572 @default.