Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319066598> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4319066598 endingPage "103776" @default.
- W4319066598 startingPage "103776" @default.
- W4319066598 abstract "In view of the faultiness that the existing image inpainting methods fail to make full use of the complete region to predict the missing region features when the object features are seriously missing, resulting in discontinuous features and fuzzy detail texture of the inpainting results, a fine inpainting method of incomplete image based on features fusion and two-steps inpainting (FFTI) is proposed in this paper. Firstly, the dynamic memory networks (DMN+) are used to fuse the external features and internal features of the incomplete image to generate the incomplete image optimization map. Secondly, a generation countermeasure generative network with gradient penalty constraints is constructed to guide the generator to rough repair the optimized incomplete image and obtain the rough repair map of the target to be repaired. Finally, the coarse repair graph is further optimized by the idea of coherence of relevant features to obtain the final fine repair graph. It is verified by simulation on three image data sets with different complexity, and compared with the existing dominant repair model for visual effect and objective data. The experimental results show that the results of the model repair in this paper are more reasonable in texture structure, better than other models in visual effect and objective data, and the Peak Signal-to-Noise Ratio of the proposed algorithm in the most challenging underwater targe dataset is 27.01, the highest Structural Similarity Index is 0.949." @default.
- W4319066598 created "2023-02-04" @default.
- W4319066598 creator A5013308685 @default.
- W4319066598 creator A5053585156 @default.
- W4319066598 creator A5064619972 @default.
- W4319066598 creator A5066850451 @default.
- W4319066598 date "2023-03-01" @default.
- W4319066598 modified "2023-10-18" @default.
- W4319066598 title "FFTI: Image inpainting algorithm via features fusion and two-steps inpainting" @default.
- W4319066598 cites W1834627138 @default.
- W4319066598 cites W1993120651 @default.
- W4319066598 cites W2055132753 @default.
- W4319066598 cites W2133665775 @default.
- W4319066598 cites W2295072214 @default.
- W4319066598 cites W2295936755 @default.
- W4319066598 cites W2331128040 @default.
- W4319066598 cites W2560920409 @default.
- W4319066598 cites W2568900804 @default.
- W4319066598 cites W2582721954 @default.
- W4319066598 cites W2613645387 @default.
- W4319066598 cites W2732026016 @default.
- W4319066598 cites W2752782242 @default.
- W4319066598 cites W2783863635 @default.
- W4319066598 cites W2798365772 @default.
- W4319066598 cites W2866634454 @default.
- W4319066598 cites W2928165649 @default.
- W4319066598 cites W2963073614 @default.
- W4319066598 cites W2963231084 @default.
- W4319066598 cites W2963255313 @default.
- W4319066598 cites W2963270367 @default.
- W4319066598 cites W2963420272 @default.
- W4319066598 cites W2965965567 @default.
- W4319066598 cites W2980794690 @default.
- W4319066598 cites W2981682056 @default.
- W4319066598 cites W2985764327 @default.
- W4319066598 cites W2997669187 @default.
- W4319066598 cites W2997763120 @default.
- W4319066598 cites W3035512475 @default.
- W4319066598 cites W3118356434 @default.
- W4319066598 doi "https://doi.org/10.1016/j.jvcir.2023.103776" @default.
- W4319066598 hasPublicationYear "2023" @default.
- W4319066598 type Work @default.
- W4319066598 citedByCount "46" @default.
- W4319066598 countsByYear W43190665982023 @default.
- W4319066598 crossrefType "journal-article" @default.
- W4319066598 hasAuthorship W4319066598A5013308685 @default.
- W4319066598 hasAuthorship W4319066598A5053585156 @default.
- W4319066598 hasAuthorship W4319066598A5064619972 @default.
- W4319066598 hasAuthorship W4319066598A5066850451 @default.
- W4319066598 hasConcept C115961682 @default.
- W4319066598 hasConcept C11727466 @default.
- W4319066598 hasConcept C121332964 @default.
- W4319066598 hasConcept C132525143 @default.
- W4319066598 hasConcept C153180895 @default.
- W4319066598 hasConcept C154945302 @default.
- W4319066598 hasConcept C163258240 @default.
- W4319066598 hasConcept C2780992000 @default.
- W4319066598 hasConcept C31972630 @default.
- W4319066598 hasConcept C41008148 @default.
- W4319066598 hasConcept C62520636 @default.
- W4319066598 hasConcept C80444323 @default.
- W4319066598 hasConceptScore W4319066598C115961682 @default.
- W4319066598 hasConceptScore W4319066598C11727466 @default.
- W4319066598 hasConceptScore W4319066598C121332964 @default.
- W4319066598 hasConceptScore W4319066598C132525143 @default.
- W4319066598 hasConceptScore W4319066598C153180895 @default.
- W4319066598 hasConceptScore W4319066598C154945302 @default.
- W4319066598 hasConceptScore W4319066598C163258240 @default.
- W4319066598 hasConceptScore W4319066598C2780992000 @default.
- W4319066598 hasConceptScore W4319066598C31972630 @default.
- W4319066598 hasConceptScore W4319066598C41008148 @default.
- W4319066598 hasConceptScore W4319066598C62520636 @default.
- W4319066598 hasConceptScore W4319066598C80444323 @default.
- W4319066598 hasLocation W43190665981 @default.
- W4319066598 hasOpenAccess W4319066598 @default.
- W4319066598 hasPrimaryLocation W43190665981 @default.
- W4319066598 hasRelatedWork W1995073329 @default.
- W4319066598 hasRelatedWork W2017457812 @default.
- W4319066598 hasRelatedWork W2060947339 @default.
- W4319066598 hasRelatedWork W2131831293 @default.
- W4319066598 hasRelatedWork W2946160871 @default.
- W4319066598 hasRelatedWork W3035059915 @default.
- W4319066598 hasRelatedWork W3103893032 @default.
- W4319066598 hasRelatedWork W425542480 @default.
- W4319066598 hasRelatedWork W49967185 @default.
- W4319066598 hasRelatedWork W3178025616 @default.
- W4319066598 hasVolume "91" @default.
- W4319066598 isParatext "false" @default.
- W4319066598 isRetracted "false" @default.
- W4319066598 workType "article" @default.