Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309771572> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4309771572 endingPage "103598" @default.
- W4309771572 startingPage "103598" @default.
- W4309771572 abstract "In infrared (IR) and visible image fusion, visual appearance of fused images produced by an end-to-end fusion network relies on a loss function that defines the desired properties of the fusion results. The previous approaches mainly focus on measuring the similarity of an output image with respective IR and visible images using pixel-wise loss functions such as mean square error or structural similarity. This can lead, however, to preserve only local information in the fused images, and it may lose semantic information in the scene. In this work, we propose a new joint loss function for the image fusion, which considers visual quality and subsequent applications simultaneously. Our joint loss function guides the fusion network by transferring the knowledge of a pre-trained network to leverage perceptual similarity. The contrast loss function serves to prevent the reduction of global and local image contrasts in the fused image. The conventional data fidelity is also considered in the proposed function. Then, the joint loss function is used to train our U-Net like fusion network, a hybrid of convolutional and transformer blocks. Experimental results show that the proposed method preserves detailed scene structure from the both of source images and demonstrates the better quantitative results. Furthermore, the proposed fusion schemes can be used for combining multi-exposure and multi-focus image pairs. To show the further effectiveness of IR and visible image fusion, we apply the results of fusion methods for downstream tasks so that the proposed method improves the cases of only using original modalities." @default.
- W4309771572 created "2022-11-29" @default.
- W4309771572 creator A5039844226 @default.
- W4309771572 creator A5060901163 @default.
- W4309771572 date "2023-01-01" @default.
- W4309771572 modified "2023-09-29" @default.
- W4309771572 title "Infrared and visible image fusion using a guiding network to leverage perceptual similarity" @default.
- W4309771572 cites W1964641132 @default.
- W4309771572 cites W2010380423 @default.
- W4309771572 cites W2031454541 @default.
- W4309771572 cites W2048913467 @default.
- W4309771572 cites W2056346283 @default.
- W4309771572 cites W2133665775 @default.
- W4309771572 cites W2152218325 @default.
- W4309771572 cites W2168783614 @default.
- W4309771572 cites W2179019672 @default.
- W4309771572 cites W2411377185 @default.
- W4309771572 cites W2532801510 @default.
- W4309771572 cites W2564077499 @default.
- W4309771572 cites W2594112328 @default.
- W4309771572 cites W2809795042 @default.
- W4309771572 cites W2928165649 @default.
- W4309771572 cites W2945776902 @default.
- W4309771572 cites W2963134949 @default.
- W4309771572 cites W2963579094 @default.
- W4309771572 cites W2963787388 @default.
- W4309771572 cites W2970073937 @default.
- W4309771572 cites W2990201382 @default.
- W4309771572 cites W3011768656 @default.
- W4309771572 cites W3026446890 @default.
- W4309771572 cites W3101573935 @default.
- W4309771572 cites W3102411220 @default.
- W4309771572 cites W3105639468 @default.
- W4309771572 cites W3181367324 @default.
- W4309771572 cites W4206713196 @default.
- W4309771572 cites W4213360337 @default.
- W4309771572 cites W4283732315 @default.
- W4309771572 cites W4312737473 @default.
- W4309771572 cites W639708223 @default.
- W4309771572 doi "https://doi.org/10.1016/j.cviu.2022.103598" @default.
- W4309771572 hasPublicationYear "2023" @default.
- W4309771572 type Work @default.
- W4309771572 citedByCount "4" @default.
- W4309771572 countsByYear W43097715722023 @default.
- W4309771572 crossrefType "journal-article" @default.
- W4309771572 hasAuthorship W4309771572A5039844226 @default.
- W4309771572 hasAuthorship W4309771572A5060901163 @default.
- W4309771572 hasConcept C103278499 @default.
- W4309771572 hasConcept C115961682 @default.
- W4309771572 hasConcept C120665830 @default.
- W4309771572 hasConcept C121332964 @default.
- W4309771572 hasConcept C138885662 @default.
- W4309771572 hasConcept C153083717 @default.
- W4309771572 hasConcept C153180895 @default.
- W4309771572 hasConcept C154945302 @default.
- W4309771572 hasConcept C158525013 @default.
- W4309771572 hasConcept C192209626 @default.
- W4309771572 hasConcept C31972630 @default.
- W4309771572 hasConcept C41008148 @default.
- W4309771572 hasConcept C41895202 @default.
- W4309771572 hasConcept C69744172 @default.
- W4309771572 hasConcept C81363708 @default.
- W4309771572 hasConceptScore W4309771572C103278499 @default.
- W4309771572 hasConceptScore W4309771572C115961682 @default.
- W4309771572 hasConceptScore W4309771572C120665830 @default.
- W4309771572 hasConceptScore W4309771572C121332964 @default.
- W4309771572 hasConceptScore W4309771572C138885662 @default.
- W4309771572 hasConceptScore W4309771572C153083717 @default.
- W4309771572 hasConceptScore W4309771572C153180895 @default.
- W4309771572 hasConceptScore W4309771572C154945302 @default.
- W4309771572 hasConceptScore W4309771572C158525013 @default.
- W4309771572 hasConceptScore W4309771572C192209626 @default.
- W4309771572 hasConceptScore W4309771572C31972630 @default.
- W4309771572 hasConceptScore W4309771572C41008148 @default.
- W4309771572 hasConceptScore W4309771572C41895202 @default.
- W4309771572 hasConceptScore W4309771572C69744172 @default.
- W4309771572 hasConceptScore W4309771572C81363708 @default.
- W4309771572 hasLocation W43097715721 @default.
- W4309771572 hasOpenAccess W4309771572 @default.
- W4309771572 hasPrimaryLocation W43097715721 @default.
- W4309771572 hasRelatedWork W2348031433 @default.
- W4309771572 hasRelatedWork W2419576664 @default.
- W4309771572 hasRelatedWork W2767651786 @default.
- W4309771572 hasRelatedWork W2884257962 @default.
- W4309771572 hasRelatedWork W2912288872 @default.
- W4309771572 hasRelatedWork W2990667865 @default.
- W4309771572 hasRelatedWork W3007420330 @default.
- W4309771572 hasRelatedWork W3045785598 @default.
- W4309771572 hasRelatedWork W4312613727 @default.
- W4309771572 hasRelatedWork W2318670660 @default.
- W4309771572 hasVolume "227" @default.
- W4309771572 isParatext "false" @default.
- W4309771572 isRetracted "false" @default.
- W4309771572 workType "article" @default.