FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285261750> ?p ?o ?g. }

• W4285261750 endingPage "20382" @default.
• W4285261750 startingPage "20368" @default.
• W4285261750 abstract "Image dehazing is a common operation in autonomous driving, traffic monitoring and surveillance. Learning-based image dehazing has achieved excellent performance recently. However, it is nearly impossible to capture pairs of hazy/clean images from the real world to train an image dehazing network. Most of existing dehazing models that are learnt from synthetically generated hazy images generalize poorly on real-world hazy scenarios due to the obvious domain shift. To deal with this unpaired problem arisen by real-world hazy images, we present Cycle Spectral Normalized Soft likelihood estimation Patch Generative Adversarial Network (Cycle-SNSPGAN) for image dehazing. Cycle-SNSPGAN is an unsupervised dehazing framework to boost the generalization ability on real-world hazy images. To leverage unpaired samples of real-world hazy images without relying on their clean counterparts, we design an SN-Soft-Patch GAN and exploit a new cyclic self-perceptual loss which avoids using the ground-truth image to compute the perceptual similarity. Moreover, a significant color loss is adopted to brighten the dehazed images as human expects. Both visual and numerical results show clear improvements of the proposed Cycle-SNSPGAN over state-of-the-arts in terms of hazy-robustness and image detail recovery, with even only a small dataset training our Cycle-SNSPGAN. Code has been available at <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://github.com/yz-wang/Cycle-SNSPGAN</uri> ." @default.
• W4285261750 created "2022-07-14" @default.
• W4285261750 creator A5003852858 @default.
• W4285261750 creator A5007144110 @default.
• W4285261750 creator A5010343572 @default.
• W4285261750 creator A5010801486 @default.
• W4285261750 creator A5015549327 @default.
• W4285261750 creator A5051555459 @default.
• W4285261750 creator A5089960389 @default.
• W4285261750 date "2022-11-01" @default.
• W4285261750 modified "2023-10-13" @default.
• W4285261750 title "Cycle-SNSPGAN: Towards Real-World Image Dehazing via Cycle Spectral Normalized Soft Likelihood Estimation Patch GAN" @default.
• W4285261750 cites W1552073401 @default.
• W4285261750 cites W1982471090 @default.
• W4285261750 cites W2028763589 @default.
• W4285261750 cites W2031624349 @default.
• W4285261750 cites W2073623229 @default.
• W4285261750 cites W2102166818 @default.
• W4285261750 cites W2114867966 @default.
• W4285261750 cites W2128254161 @default.
• W4285261750 cites W2147318913 @default.
• W4285261750 cites W2156936307 @default.
• W4285261750 cites W2170965888 @default.
• W4285261750 cites W2194775991 @default.
• W4285261750 cites W2239857079 @default.
• W4285261750 cites W2256362396 @default.
• W4285261750 cites W2467473805 @default.
• W4285261750 cites W2519481857 @default.
• W4285261750 cites W2536722097 @default.
• W4285261750 cites W2593414223 @default.
• W4285261750 cites W2607202125 @default.
• W4285261750 cites W2752782242 @default.
• W4285261750 cites W2770637285 @default.
• W4285261750 cites W2779176852 @default.
• W4285261750 cites W2798876216 @default.
• W4285261750 cites W2808370801 @default.
• W4285261750 cites W2866634454 @default.
• W4285261750 cites W2892503698 @default.
• W4285261750 cites W2894938704 @default.
• W4285261750 cites W2902495740 @default.
• W4285261750 cites W2948606054 @default.
• W4285261750 cites W2955731188 @default.
• W4285261750 cites W2962754725 @default.
• W4285261750 cites W2962793481 @default.
• W4285261750 cites W2963017889 @default.
• W4285261750 cites W2963073614 @default.
• W4285261750 cites W2963074253 @default.
• W4285261750 cites W2963152299 @default.
• W4285261750 cites W2963306157 @default.
• W4285261750 cites W2963470893 @default.
• W4285261750 cites W2963928582 @default.
• W4285261750 cites W2970360808 @default.
• W4285261750 cites W2976715267 @default.
• W4285261750 cites W2979261558 @default.
• W4285261750 cites W2983339877 @default.
• W4285261750 cites W2985194834 @default.
• W4285261750 cites W2997210448 @default.
• W4285261750 cites W2998249728 @default.
• W4285261750 cites W2999501504 @default.
• W4285261750 cites W3034331889 @default.
• W4285261750 cites W3034578106 @default.
• W4285261750 cites W3035601380 @default.
• W4285261750 cites W3098546057 @default.
• W4285261750 cites W3121661546 @default.
• W4285261750 cites W3135542706 @default.
• W4285261750 cites W3174756006 @default.
• W4285261750 cites W3174849075 @default.
• W4285261750 cites W4214666412 @default.
• W4285261750 doi "https://doi.org/10.1109/tits.2022.3170328" @default.
• W4285261750 hasPublicationYear "2022" @default.
• W4285261750 type Work @default.
• W4285261750 citedByCount "9" @default.
• W4285261750 countsByYear W42852617502023 @default.
• W4285261750 crossrefType "journal-article" @default.
• W4285261750 hasAuthorship W4285261750A5003852858 @default.
• W4285261750 hasAuthorship W4285261750A5007144110 @default.
• W4285261750 hasAuthorship W4285261750A5010343572 @default.
• W4285261750 hasAuthorship W4285261750A5010801486 @default.
• W4285261750 hasAuthorship W4285261750A5015549327 @default.
• W4285261750 hasAuthorship W4285261750A5051555459 @default.
• W4285261750 hasAuthorship W4285261750A5089960389 @default.
• W4285261750 hasConcept C104317684 @default.
• W4285261750 hasConcept C115961682 @default.
• W4285261750 hasConcept C153083717 @default.
• W4285261750 hasConcept C154945302 @default.
• W4285261750 hasConcept C185592680 @default.
• W4285261750 hasConcept C2776674983 @default.
• W4285261750 hasConcept C31972630 @default.
• W4285261750 hasConcept C41008148 @default.
• W4285261750 hasConcept C55493867 @default.
• W4285261750 hasConcept C63479239 @default.
• W4285261750 hasConceptScore W4285261750C104317684 @default.
• W4285261750 hasConceptScore W4285261750C115961682 @default.
• W4285261750 hasConceptScore W4285261750C153083717 @default.
• W4285261750 hasConceptScore W4285261750C154945302 @default.
• W4285261750 hasConceptScore W4285261750C185592680 @default.
• W4285261750 hasConceptScore W4285261750C2776674983 @default.
• W4285261750 hasConceptScore W4285261750C31972630 @default.

• next