Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304080507> ?p ?o ?g. }
- W4304080507 abstract "Very recently, with the development of underwater robots, underwater image enhancement arising growing interests in the computer vision community. However, owing to light being scattered and absorbed while it traveling in water, underwater captured images often suffer from color cast and low visibility. Existing methods depend on specific prior knowledge and training data to enhance underwater images in the absence of structure information, which results in poor and unnatural performance. To this end, we propose a Structural-Inferred Bi-level Model (SIBM) that incorporates different modalities of knowledge (i.e., semantic domain, gradient-domain, and pixel domain) hierarchically enhancing underwater images. In particular, by introducing a semantic mask, we individually optimize the forehand branch that avoids unnecessary interference arising from the background region. We design a gradient-based high-frequency branch to exploit gradient-space guidance for preserving texture structures. Moreover, we construct a pixel-based branch by feeding semantic and gradient information to enhance underwater images. To exploit different modalities, we introduce a hyper-parameter optimization scheme to fuse the above domain information. Experimental results illustrate that the developed method not only outperforms the previous methods in quantitative scores but also generalizes well on real-world underwater datasets. Source code is available at hrefhttps://github.com/IntegralCoCo/SIBM https://github.com/IntegralCoCo/SIBM." @default.
- W4304080507 created "2022-10-10" @default.
- W4304080507 creator A5006040955 @default.
- W4304080507 creator A5013768600 @default.
- W4304080507 creator A5023345994 @default.
- W4304080507 date "2022-10-10" @default.
- W4304080507 modified "2023-09-27" @default.
- W4304080507 title "Structure-Inferred Bi-level Model for Underwater Image Enhancement" @default.
- W4304080507 cites W1970163214 @default.
- W4304080507 cites W2081140338 @default.
- W4304080507 cites W2102166818 @default.
- W4304080507 cites W2107858703 @default.
- W4304080507 cites W2141303451 @default.
- W4304080507 cites W2181646778 @default.
- W4304080507 cites W2192254709 @default.
- W4304080507 cites W2216874664 @default.
- W4304080507 cites W2474516010 @default.
- W4304080507 cites W2523532944 @default.
- W4304080507 cites W2587107113 @default.
- W4304080507 cites W2596058005 @default.
- W4304080507 cites W2794405642 @default.
- W4304080507 cites W2798898057 @default.
- W4304080507 cites W2950055287 @default.
- W4304080507 cites W2950524558 @default.
- W4304080507 cites W2963420686 @default.
- W4304080507 cites W2963928582 @default.
- W4304080507 cites W2971483169 @default.
- W4304080507 cites W2989207674 @default.
- W4304080507 cites W2990176100 @default.
- W4304080507 cites W2991377405 @default.
- W4304080507 cites W2997763120 @default.
- W4304080507 cites W3006777311 @default.
- W4304080507 cites W3009406242 @default.
- W4304080507 cites W3015225761 @default.
- W4304080507 cites W3035563424 @default.
- W4304080507 cites W3106725490 @default.
- W4304080507 cites W3127655102 @default.
- W4304080507 cites W3127968388 @default.
- W4304080507 cites W3159660641 @default.
- W4304080507 cites W3169767072 @default.
- W4304080507 cites W3201231642 @default.
- W4304080507 cites W3205291758 @default.
- W4304080507 cites W4205293988 @default.
- W4304080507 cites W4213110992 @default.
- W4304080507 cites W4283808395 @default.
- W4304080507 cites W4285228564 @default.
- W4304080507 doi "https://doi.org/10.1145/3503161.3548087" @default.
- W4304080507 hasPublicationYear "2022" @default.
- W4304080507 type Work @default.
- W4304080507 citedByCount "3" @default.
- W4304080507 countsByYear W43040805072023 @default.
- W4304080507 crossrefType "proceedings-article" @default.
- W4304080507 hasAuthorship W4304080507A5006040955 @default.
- W4304080507 hasAuthorship W4304080507A5013768600 @default.
- W4304080507 hasAuthorship W4304080507A5023345994 @default.
- W4304080507 hasConcept C111368507 @default.
- W4304080507 hasConcept C115961682 @default.
- W4304080507 hasConcept C119599485 @default.
- W4304080507 hasConcept C120665830 @default.
- W4304080507 hasConcept C121332964 @default.
- W4304080507 hasConcept C123403432 @default.
- W4304080507 hasConcept C127162648 @default.
- W4304080507 hasConcept C127313418 @default.
- W4304080507 hasConcept C127413603 @default.
- W4304080507 hasConcept C134306372 @default.
- W4304080507 hasConcept C141353440 @default.
- W4304080507 hasConcept C144024400 @default.
- W4304080507 hasConcept C154945302 @default.
- W4304080507 hasConcept C160633673 @default.
- W4304080507 hasConcept C165696696 @default.
- W4304080507 hasConcept C177264268 @default.
- W4304080507 hasConcept C199360897 @default.
- W4304080507 hasConcept C2776760102 @default.
- W4304080507 hasConcept C2779903281 @default.
- W4304080507 hasConcept C31972630 @default.
- W4304080507 hasConcept C32022120 @default.
- W4304080507 hasConcept C33923547 @default.
- W4304080507 hasConcept C36289849 @default.
- W4304080507 hasConcept C36503486 @default.
- W4304080507 hasConcept C38652104 @default.
- W4304080507 hasConcept C41008148 @default.
- W4304080507 hasConcept C76155785 @default.
- W4304080507 hasConcept C98083399 @default.
- W4304080507 hasConceptScore W4304080507C111368507 @default.
- W4304080507 hasConceptScore W4304080507C115961682 @default.
- W4304080507 hasConceptScore W4304080507C119599485 @default.
- W4304080507 hasConceptScore W4304080507C120665830 @default.
- W4304080507 hasConceptScore W4304080507C121332964 @default.
- W4304080507 hasConceptScore W4304080507C123403432 @default.
- W4304080507 hasConceptScore W4304080507C127162648 @default.
- W4304080507 hasConceptScore W4304080507C127313418 @default.
- W4304080507 hasConceptScore W4304080507C127413603 @default.
- W4304080507 hasConceptScore W4304080507C134306372 @default.
- W4304080507 hasConceptScore W4304080507C141353440 @default.
- W4304080507 hasConceptScore W4304080507C144024400 @default.
- W4304080507 hasConceptScore W4304080507C154945302 @default.
- W4304080507 hasConceptScore W4304080507C160633673 @default.
- W4304080507 hasConceptScore W4304080507C165696696 @default.
- W4304080507 hasConceptScore W4304080507C177264268 @default.
- W4304080507 hasConceptScore W4304080507C199360897 @default.