Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380994055> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4380994055 abstract "Due to the light absorption and scattering induced by the water medium, underwater images usually suffer from some degradation problems, such as low contrast, color distortion, and blurring details, which aggravate the difficulty of downstream underwater understanding tasks. Therefore, how to obtain clear and visually pleasant images has become a common concern of people, and the task of underwater image enhancement (UIE) has also emerged as the times require. Among existing UIE methods, Generative Adversarial Networks (GANs) based methods perform well in visual aesthetics, while the physical model-based methods have better scene adaptability. Inheriting the advantages of the above two types of models, we propose a physical model-guided GAN model for UIE in this paper, referred to as PUGAN. The entire network is under the GAN architecture. On the one hand, we design a Parameters Estimation subnetwork (Par-subnet) to learn the parameters for physical model inversion, and use the generated color enhancement image as auxiliary information for the Two-Stream Interaction Enhancement sub-network (TSIE-subnet). Meanwhile, we design a Degradation Quantization (DQ) module in TSIE-subnet to quantize scene degradation, thereby achieving reinforcing enhancement of key regions. On the other hand, we design the Dual-Discriminators for the style-content adversarial constraint, promoting the authenticity and visual aesthetics of the results. Extensive experiments on three benchmark datasets demonstrate that our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics." @default.
- W4380994055 created "2023-06-17" @default.
- W4380994055 creator A5008386708 @default.
- W4380994055 creator A5028597017 @default.
- W4380994055 creator A5034122071 @default.
- W4380994055 creator A5077088563 @default.
- W4380994055 creator A5086639598 @default.
- W4380994055 creator A5090237325 @default.
- W4380994055 creator A5091558139 @default.
- W4380994055 date "2023-06-15" @default.
- W4380994055 modified "2023-09-27" @default.
- W4380994055 title "PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators" @default.
- W4380994055 doi "https://doi.org/10.48550/arxiv.2306.08918" @default.
- W4380994055 hasPublicationYear "2023" @default.
- W4380994055 type Work @default.
- W4380994055 citedByCount "0" @default.
- W4380994055 crossrefType "posted-content" @default.
- W4380994055 hasAuthorship W4380994055A5008386708 @default.
- W4380994055 hasAuthorship W4380994055A5028597017 @default.
- W4380994055 hasAuthorship W4380994055A5034122071 @default.
- W4380994055 hasAuthorship W4380994055A5077088563 @default.
- W4380994055 hasAuthorship W4380994055A5086639598 @default.
- W4380994055 hasAuthorship W4380994055A5090237325 @default.
- W4380994055 hasAuthorship W4380994055A5091558139 @default.
- W4380994055 hasBestOaLocation W43809940551 @default.
- W4380994055 hasConcept C111368507 @default.
- W4380994055 hasConcept C127313418 @default.
- W4380994055 hasConcept C154945302 @default.
- W4380994055 hasConcept C21099817 @default.
- W4380994055 hasConcept C31258907 @default.
- W4380994055 hasConcept C31972630 @default.
- W4380994055 hasConcept C41008148 @default.
- W4380994055 hasConcept C98083399 @default.
- W4380994055 hasConceptScore W4380994055C111368507 @default.
- W4380994055 hasConceptScore W4380994055C127313418 @default.
- W4380994055 hasConceptScore W4380994055C154945302 @default.
- W4380994055 hasConceptScore W4380994055C21099817 @default.
- W4380994055 hasConceptScore W4380994055C31258907 @default.
- W4380994055 hasConceptScore W4380994055C31972630 @default.
- W4380994055 hasConceptScore W4380994055C41008148 @default.
- W4380994055 hasConceptScore W4380994055C98083399 @default.
- W4380994055 hasLocation W43809940551 @default.
- W4380994055 hasOpenAccess W4380994055 @default.
- W4380994055 hasPrimaryLocation W43809940551 @default.
- W4380994055 hasRelatedWork W1647058919 @default.
- W4380994055 hasRelatedWork W1891287906 @default.
- W4380994055 hasRelatedWork W2030806501 @default.
- W4380994055 hasRelatedWork W2036807459 @default.
- W4380994055 hasRelatedWork W2390043387 @default.
- W4380994055 hasRelatedWork W2433210372 @default.
- W4380994055 hasRelatedWork W2742702720 @default.
- W4380994055 hasRelatedWork W2897935372 @default.
- W4380994055 hasRelatedWork W4367016407 @default.
- W4380994055 hasRelatedWork W2607471452 @default.
- W4380994055 isParatext "false" @default.
- W4380994055 isRetracted "false" @default.
- W4380994055 workType "article" @default.