Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327723892> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4327723892 abstract "Abstract Influenced by light scattering, absorption and water impurities, the quality of underwater image is so poor that it poses a great challenge to underwater target detection, marine biological research and marine exploration. Thus, significant attention on underwater image enhancement (UIE) has been attracted for producing high quality visuality as if the underwater image was taken in-air without any structure, texture and color loss. To solve this issue, previous work mainly focus on supervised-learning with large amount of paired data, which is more demanding in practical application. Recent Cycle-GAN based UIE break through the dependence on paired data but easily trap in mapping ambiguity. Essentially, two-sided cycle-consistency is a bijection and only focuses on the pixel level, which is too restrictive and can not accurately express underwater scene structure. Besides, high frequencies in reference images tend to be eschewed by generator, making it difficult to synthesize authentic textures and colors of underwater images. We therefore propose a novel unconstrained UIE framework, structure-frequency-aware generative adversarial network (SFA-GAN), which not only accurately preserves the structure of low quality underwater images, but also captures the high frequencies of the reference images under unconstrained settings. Extensive experiments on datasets EUVP, UFO-120 and UIEB demonstrate that the proposed SFA-GAN can achieves state-of-art results on some metrics and produce more clear underwater images without sacrificing model complexity." @default.
- W4327723892 created "2023-03-18" @default.
- W4327723892 creator A5014863753 @default.
- W4327723892 creator A5042990010 @default.
- W4327723892 creator A5056877980 @default.
- W4327723892 creator A5074387543 @default.
- W4327723892 date "2023-03-17" @default.
- W4327723892 modified "2023-10-17" @default.
- W4327723892 title "SFA-GAN: Structure-frequency-aware generative adversarial network for underwater image enhancement" @default.
- W4327723892 cites W2033098034 @default.
- W4327723892 cites W2055726479 @default.
- W4327723892 cites W2181646778 @default.
- W4327723892 cites W2474516010 @default.
- W4327723892 cites W2523532944 @default.
- W4327723892 cites W2587107113 @default.
- W4327723892 cites W2763503841 @default.
- W4327723892 cites W2891501856 @default.
- W4327723892 cites W2971483169 @default.
- W4327723892 cites W2990176100 @default.
- W4327723892 cites W3006777311 @default.
- W4327723892 cites W3093505672 @default.
- W4327723892 cites W3099562471 @default.
- W4327723892 cites W3100498948 @default.
- W4327723892 doi "https://doi.org/10.21203/rs.3.rs-2645623/v1" @default.
- W4327723892 hasPublicationYear "2023" @default.
- W4327723892 type Work @default.
- W4327723892 citedByCount "0" @default.
- W4327723892 crossrefType "posted-content" @default.
- W4327723892 hasAuthorship W4327723892A5014863753 @default.
- W4327723892 hasAuthorship W4327723892A5042990010 @default.
- W4327723892 hasAuthorship W4327723892A5056877980 @default.
- W4327723892 hasAuthorship W4327723892A5074387543 @default.
- W4327723892 hasBestOaLocation W43277238921 @default.
- W4327723892 hasConcept C115961682 @default.
- W4327723892 hasConcept C153180895 @default.
- W4327723892 hasConcept C154945302 @default.
- W4327723892 hasConcept C166957645 @default.
- W4327723892 hasConcept C205649164 @default.
- W4327723892 hasConcept C31972630 @default.
- W4327723892 hasConcept C41008148 @default.
- W4327723892 hasConcept C55020928 @default.
- W4327723892 hasConcept C98083399 @default.
- W4327723892 hasConceptScore W4327723892C115961682 @default.
- W4327723892 hasConceptScore W4327723892C153180895 @default.
- W4327723892 hasConceptScore W4327723892C154945302 @default.
- W4327723892 hasConceptScore W4327723892C166957645 @default.
- W4327723892 hasConceptScore W4327723892C205649164 @default.
- W4327723892 hasConceptScore W4327723892C31972630 @default.
- W4327723892 hasConceptScore W4327723892C41008148 @default.
- W4327723892 hasConceptScore W4327723892C55020928 @default.
- W4327723892 hasConceptScore W4327723892C98083399 @default.
- W4327723892 hasLocation W43277238921 @default.
- W4327723892 hasOpenAccess W4327723892 @default.
- W4327723892 hasPrimaryLocation W43277238921 @default.
- W4327723892 hasRelatedWork W1647058919 @default.
- W4327723892 hasRelatedWork W2005185696 @default.
- W4327723892 hasRelatedWork W2030806501 @default.
- W4327723892 hasRelatedWork W2161229648 @default.
- W4327723892 hasRelatedWork W2433210372 @default.
- W4327723892 hasRelatedWork W2574052219 @default.
- W4327723892 hasRelatedWork W2742702720 @default.
- W4327723892 hasRelatedWork W2897935372 @default.
- W4327723892 hasRelatedWork W4367016407 @default.
- W4327723892 hasRelatedWork W2607471452 @default.
- W4327723892 isParatext "false" @default.
- W4327723892 isRetracted "false" @default.
- W4327723892 workType "article" @default.