Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380079464> ?p ?o ?g. }
- W4380079464 endingPage "1195" @default.
- W4380079464 startingPage "1195" @default.
- W4380079464 abstract "Underwater images often suffer from degradation due to scattering and absorption. With the development of artificial intelligence, fully supervised learning-based models have been widely adopted to solve this problem. However, the enhancement performance is susceptible to the quality of the reference images, which is more pronounced in underwater image enhancement tasks because the ground truths are not available. In this paper, we propose a light-enhanced pixel fusion network (LEPF-Net) to solve this problem. Specifically, we first introduce a novel light enhancement block (LEB) based on the residual block (RB) and the light enhancement curve (LE-Curve) to restore the cast color of the images. The RB is adopted to learn and obtain the feature maps from an original input image, and the LE-Curve is used to renovate the color cast of the learned images. To realize the superb detail of the repaired images, which is superior to the reference images, we develop a pixel fusion subnetwork (PF-SubNet) that adopts a pixel attention mechanism (PAM) to eliminate noise from the underwater image. The PAM adapts weight allocation to different levels of a feature map, which leads to an enhancement in the visibility of severely degraded areas. The experimental results show that the proposed LEPF-Net outperforms most of the existing underwater image enhancement methods. Furthermore, among the five classic no-reference image quality assessment (NRIQA) indicators, the enhanced images obtained by LEPF-Net are of higher quality than the ground truths from the UIEB dataset." @default.
- W4380079464 created "2023-06-10" @default.
- W4380079464 creator A5003990951 @default.
- W4380079464 creator A5005638593 @default.
- W4380079464 creator A5034852420 @default.
- W4380079464 creator A5056028210 @default.
- W4380079464 creator A5066546843 @default.
- W4380079464 creator A5075063242 @default.
- W4380079464 date "2023-06-08" @default.
- W4380079464 modified "2023-09-28" @default.
- W4380079464 title "LEPF-Net: Light Enhancement Pixel Fusion Network for Underwater Image Enhancement" @default.
- W4380079464 cites W1963696504 @default.
- W4380079464 cites W2001412060 @default.
- W4380079464 cites W2041285268 @default.
- W4380079464 cites W2076205488 @default.
- W4380079464 cites W2082968119 @default.
- W4380079464 cites W2102166818 @default.
- W4380079464 cites W2163370434 @default.
- W4380079464 cites W2181646778 @default.
- W4380079464 cites W2194775991 @default.
- W4380079464 cites W2293581118 @default.
- W4380079464 cites W2596058005 @default.
- W4380079464 cites W2783488367 @default.
- W4380079464 cites W2792328492 @default.
- W4380079464 cites W2892845027 @default.
- W4380079464 cites W2896671317 @default.
- W4380079464 cites W2942199210 @default.
- W4380079464 cites W2950055287 @default.
- W4380079464 cites W2964088115 @default.
- W4380079464 cites W2990176100 @default.
- W4380079464 cites W2995978867 @default.
- W4380079464 cites W3001735056 @default.
- W4380079464 cites W3032766569 @default.
- W4380079464 cites W3153781409 @default.
- W4380079464 cites W3180134609 @default.
- W4380079464 cites W3195766574 @default.
- W4380079464 cites W3205185163 @default.
- W4380079464 cites W3214119378 @default.
- W4380079464 cites W4211198541 @default.
- W4380079464 cites W4213110992 @default.
- W4380079464 cites W4220654161 @default.
- W4380079464 cites W4224219537 @default.
- W4380079464 cites W4225309680 @default.
- W4380079464 cites W4281262963 @default.
- W4380079464 cites W4281718770 @default.
- W4380079464 cites W4283521894 @default.
- W4380079464 cites W4294871818 @default.
- W4380079464 cites W4294891618 @default.
- W4380079464 cites W4353065573 @default.
- W4380079464 cites W4353091370 @default.
- W4380079464 cites W4360603643 @default.
- W4380079464 cites W4362609184 @default.
- W4380079464 cites W806756867 @default.
- W4380079464 doi "https://doi.org/10.3390/jmse11061195" @default.
- W4380079464 hasPublicationYear "2023" @default.
- W4380079464 type Work @default.
- W4380079464 citedByCount "0" @default.
- W4380079464 crossrefType "journal-article" @default.
- W4380079464 hasAuthorship W4380079464A5003990951 @default.
- W4380079464 hasAuthorship W4380079464A5005638593 @default.
- W4380079464 hasAuthorship W4380079464A5034852420 @default.
- W4380079464 hasAuthorship W4380079464A5056028210 @default.
- W4380079464 hasAuthorship W4380079464A5066546843 @default.
- W4380079464 hasAuthorship W4380079464A5075063242 @default.
- W4380079464 hasBestOaLocation W43800794641 @default.
- W4380079464 hasConcept C106430172 @default.
- W4380079464 hasConcept C111368507 @default.
- W4380079464 hasConcept C11413529 @default.
- W4380079464 hasConcept C115961682 @default.
- W4380079464 hasConcept C120665830 @default.
- W4380079464 hasConcept C121332964 @default.
- W4380079464 hasConcept C123403432 @default.
- W4380079464 hasConcept C127313418 @default.
- W4380079464 hasConcept C138885662 @default.
- W4380079464 hasConcept C153180895 @default.
- W4380079464 hasConcept C154945302 @default.
- W4380079464 hasConcept C155512373 @default.
- W4380079464 hasConcept C160633673 @default.
- W4380079464 hasConcept C2524010 @default.
- W4380079464 hasConcept C2776401178 @default.
- W4380079464 hasConcept C2777210771 @default.
- W4380079464 hasConcept C3017601658 @default.
- W4380079464 hasConcept C31972630 @default.
- W4380079464 hasConcept C33923547 @default.
- W4380079464 hasConcept C41008148 @default.
- W4380079464 hasConcept C41895202 @default.
- W4380079464 hasConcept C55020928 @default.
- W4380079464 hasConcept C69744172 @default.
- W4380079464 hasConcept C9417928 @default.
- W4380079464 hasConcept C98083399 @default.
- W4380079464 hasConceptScore W4380079464C106430172 @default.
- W4380079464 hasConceptScore W4380079464C111368507 @default.
- W4380079464 hasConceptScore W4380079464C11413529 @default.
- W4380079464 hasConceptScore W4380079464C115961682 @default.
- W4380079464 hasConceptScore W4380079464C120665830 @default.
- W4380079464 hasConceptScore W4380079464C121332964 @default.
- W4380079464 hasConceptScore W4380079464C123403432 @default.
- W4380079464 hasConceptScore W4380079464C127313418 @default.