Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386002570> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4386002570 endingPage "109225" @default.
- W4386002570 startingPage "109225" @default.
- W4386002570 abstract "Currently, most dehazing-based deep approaches are developed as an end-to-end manner to reconstruct a degraded image in an unintelligible fashion. For these dehazing models, the absence of ‘Credible Modeling’ to guide the network design is a barrier to be applied commercially in the open-world. To address this problem, we introduce the Taylor approximation principle as the soul and materialize this principle with the help of the Laplacian Pyramid. Specifically, we assume that the N paths of Laplacian pyramid model correspond to the N terms (sub-functions) in Taylor’s theorem. We attempt to use bottom paths and top paths to reconstruct the low-/high-frequency information of the clear image, respectively. Further, we develop a T-Unet module that focuses on regularizing the feature maps generated at bottom paths and design an attention sharing weight K to help approximate the Taylor high-order terms. Extensive experimental results demonstrate that our approach can run a 4K image on a single GPU with 24G RAM in real-time (80fps) and have unparalleled interpretability. The url of our code at https://github.com/zzr-idam/Interpretable-Pyramid-Network." @default.
- W4386002570 created "2023-08-20" @default.
- W4386002570 creator A5019757549 @default.
- W4386002570 creator A5045065594 @default.
- W4386002570 creator A5055033347 @default.
- W4386002570 creator A5072069474 @default.
- W4386002570 creator A5077971554 @default.
- W4386002570 date "2024-01-01" @default.
- W4386002570 modified "2023-10-17" @default.
- W4386002570 title "Single UHD image dehazing via Interpretable Pyramid Network" @default.
- W4386002570 cites W2009667331 @default.
- W4386002570 cites W2024165284 @default.
- W4386002570 cites W2032389377 @default.
- W4386002570 cites W2133665775 @default.
- W4386002570 cites W2568283272 @default.
- W4386002570 cites W2792830341 @default.
- W4386002570 cites W2962782447 @default.
- W4386002570 cites W2963037989 @default.
- W4386002570 cites W2973007605 @default.
- W4386002570 cites W3135542706 @default.
- W4386002570 cites W3194668998 @default.
- W4386002570 cites W4312958254 @default.
- W4386002570 cites W4327808545 @default.
- W4386002570 doi "https://doi.org/10.1016/j.sigpro.2023.109225" @default.
- W4386002570 hasPublicationYear "2024" @default.
- W4386002570 type Work @default.
- W4386002570 citedByCount "0" @default.
- W4386002570 crossrefType "journal-article" @default.
- W4386002570 hasAuthorship W4386002570A5019757549 @default.
- W4386002570 hasAuthorship W4386002570A5045065594 @default.
- W4386002570 hasAuthorship W4386002570A5055033347 @default.
- W4386002570 hasAuthorship W4386002570A5072069474 @default.
- W4386002570 hasAuthorship W4386002570A5077971554 @default.
- W4386002570 hasBestOaLocation W43860025702 @default.
- W4386002570 hasConcept C11413529 @default.
- W4386002570 hasConcept C115961682 @default.
- W4386002570 hasConcept C134306372 @default.
- W4386002570 hasConcept C138885662 @default.
- W4386002570 hasConcept C142575187 @default.
- W4386002570 hasConcept C154945302 @default.
- W4386002570 hasConcept C158946198 @default.
- W4386002570 hasConcept C165700671 @default.
- W4386002570 hasConcept C177264268 @default.
- W4386002570 hasConcept C199360897 @default.
- W4386002570 hasConcept C2524010 @default.
- W4386002570 hasConcept C2776401178 @default.
- W4386002570 hasConcept C2776760102 @default.
- W4386002570 hasConcept C2781067378 @default.
- W4386002570 hasConcept C31972630 @default.
- W4386002570 hasConcept C33923547 @default.
- W4386002570 hasConcept C41008148 @default.
- W4386002570 hasConcept C41895202 @default.
- W4386002570 hasConcept C80444323 @default.
- W4386002570 hasConceptScore W4386002570C11413529 @default.
- W4386002570 hasConceptScore W4386002570C115961682 @default.
- W4386002570 hasConceptScore W4386002570C134306372 @default.
- W4386002570 hasConceptScore W4386002570C138885662 @default.
- W4386002570 hasConceptScore W4386002570C142575187 @default.
- W4386002570 hasConceptScore W4386002570C154945302 @default.
- W4386002570 hasConceptScore W4386002570C158946198 @default.
- W4386002570 hasConceptScore W4386002570C165700671 @default.
- W4386002570 hasConceptScore W4386002570C177264268 @default.
- W4386002570 hasConceptScore W4386002570C199360897 @default.
- W4386002570 hasConceptScore W4386002570C2524010 @default.
- W4386002570 hasConceptScore W4386002570C2776401178 @default.
- W4386002570 hasConceptScore W4386002570C2776760102 @default.
- W4386002570 hasConceptScore W4386002570C2781067378 @default.
- W4386002570 hasConceptScore W4386002570C31972630 @default.
- W4386002570 hasConceptScore W4386002570C33923547 @default.
- W4386002570 hasConceptScore W4386002570C41008148 @default.
- W4386002570 hasConceptScore W4386002570C41895202 @default.
- W4386002570 hasConceptScore W4386002570C80444323 @default.
- W4386002570 hasFunder F4320321001 @default.
- W4386002570 hasFunder F4320324174 @default.
- W4386002570 hasLocation W43860025701 @default.
- W4386002570 hasLocation W43860025702 @default.
- W4386002570 hasOpenAccess W4386002570 @default.
- W4386002570 hasPrimaryLocation W43860025701 @default.
- W4386002570 hasRelatedWork W2085686114 @default.
- W4386002570 hasRelatedWork W2806259446 @default.
- W4386002570 hasRelatedWork W2905433371 @default.
- W4386002570 hasRelatedWork W4226258012 @default.
- W4386002570 hasRelatedWork W4310278675 @default.
- W4386002570 hasRelatedWork W4311431240 @default.
- W4386002570 hasRelatedWork W4312407344 @default.
- W4386002570 hasRelatedWork W4361193272 @default.
- W4386002570 hasRelatedWork W4384115502 @default.
- W4386002570 hasRelatedWork W2963326959 @default.
- W4386002570 hasVolume "214" @default.
- W4386002570 isParatext "false" @default.
- W4386002570 isRetracted "false" @default.
- W4386002570 workType "article" @default.