Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081097499> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3081097499 endingPage "5898" @default.
- W3081097499 startingPage "5898" @default.
- W3081097499 abstract "In this paper, we propose an enhanced pix2pix dehazing network, which generates clear images without relying on a physical scattering model. This network is a generative adversarial network (GAN) which combines multiple guided filter layers. First, the input of hazy images is smoothed to obtain high-frequency features according to different smoothing kernels of the guided filter layer. Then, these features are embedded in higher dimensions of the network and connected with the output of the generator’s encoder. Finally, Visual Geometry Group (VGG) features are introduced to serve as a loss function to improve the quality of the texture information restoration and generate better hazy-free images. We conduct experiments on NYU-Depth, I-HAZE and O-HAZE datasets. The enhanced pix2pix dehazing network we propose produces increases of 1.22 dB in the Peak Signal-to-Noise Ratio (PSNR) and 0.01 in the Structural Similarity Index Metric (SSIM) compared with a second successful comparison method using the indoor test dataset. Extensive experiments demonstrate that the proposed method has good performance for image dehazing." @default.
- W3081097499 created "2020-09-01" @default.
- W3081097499 creator A5011137663 @default.
- W3081097499 creator A5045150570 @default.
- W3081097499 creator A5045546082 @default.
- W3081097499 creator A5052007042 @default.
- W3081097499 creator A5060435114 @default.
- W3081097499 date "2020-08-26" @default.
- W3081097499 modified "2023-10-18" @default.
- W3081097499 title "An Enhanced pix2pix Dehazing Network with Guided Filter Layer" @default.
- W3081097499 cites W2002299629 @default.
- W3081097499 cites W2028990532 @default.
- W3081097499 cites W2121880036 @default.
- W3081097499 cites W2156936307 @default.
- W3081097499 cites W2256362396 @default.
- W3081097499 cites W2584526915 @default.
- W3081097499 cites W2912104034 @default.
- W3081097499 cites W2963017889 @default.
- W3081097499 cites W2963928582 @default.
- W3081097499 cites W2995754325 @default.
- W3081097499 doi "https://doi.org/10.3390/app10175898" @default.
- W3081097499 hasPublicationYear "2020" @default.
- W3081097499 type Work @default.
- W3081097499 sameAs 3081097499 @default.
- W3081097499 citedByCount "4" @default.
- W3081097499 countsByYear W30810974992021 @default.
- W3081097499 countsByYear W30810974992022 @default.
- W3081097499 countsByYear W30810974992023 @default.
- W3081097499 crossrefType "journal-article" @default.
- W3081097499 hasAuthorship W3081097499A5011137663 @default.
- W3081097499 hasAuthorship W3081097499A5045150570 @default.
- W3081097499 hasAuthorship W3081097499A5045546082 @default.
- W3081097499 hasAuthorship W3081097499A5052007042 @default.
- W3081097499 hasAuthorship W3081097499A5060435114 @default.
- W3081097499 hasBestOaLocation W30810974991 @default.
- W3081097499 hasConcept C103278499 @default.
- W3081097499 hasConcept C106131492 @default.
- W3081097499 hasConcept C111919701 @default.
- W3081097499 hasConcept C115961682 @default.
- W3081097499 hasConcept C118505674 @default.
- W3081097499 hasConcept C153180895 @default.
- W3081097499 hasConcept C154945302 @default.
- W3081097499 hasConcept C162324750 @default.
- W3081097499 hasConcept C176217482 @default.
- W3081097499 hasConcept C21547014 @default.
- W3081097499 hasConcept C31972630 @default.
- W3081097499 hasConcept C3770464 @default.
- W3081097499 hasConcept C41008148 @default.
- W3081097499 hasConceptScore W3081097499C103278499 @default.
- W3081097499 hasConceptScore W3081097499C106131492 @default.
- W3081097499 hasConceptScore W3081097499C111919701 @default.
- W3081097499 hasConceptScore W3081097499C115961682 @default.
- W3081097499 hasConceptScore W3081097499C118505674 @default.
- W3081097499 hasConceptScore W3081097499C153180895 @default.
- W3081097499 hasConceptScore W3081097499C154945302 @default.
- W3081097499 hasConceptScore W3081097499C162324750 @default.
- W3081097499 hasConceptScore W3081097499C176217482 @default.
- W3081097499 hasConceptScore W3081097499C21547014 @default.
- W3081097499 hasConceptScore W3081097499C31972630 @default.
- W3081097499 hasConceptScore W3081097499C3770464 @default.
- W3081097499 hasConceptScore W3081097499C41008148 @default.
- W3081097499 hasIssue "17" @default.
- W3081097499 hasLocation W30810974991 @default.
- W3081097499 hasOpenAccess W3081097499 @default.
- W3081097499 hasPrimaryLocation W30810974991 @default.
- W3081097499 hasRelatedWork W1983340871 @default.
- W3081097499 hasRelatedWork W2005185696 @default.
- W3081097499 hasRelatedWork W2036778696 @default.
- W3081097499 hasRelatedWork W2130228941 @default.
- W3081097499 hasRelatedWork W2161229648 @default.
- W3081097499 hasRelatedWork W2235753890 @default.
- W3081097499 hasRelatedWork W2993674027 @default.
- W3081097499 hasRelatedWork W3090091644 @default.
- W3081097499 hasRelatedWork W4286783870 @default.
- W3081097499 hasRelatedWork W4378531051 @default.
- W3081097499 hasVolume "10" @default.
- W3081097499 isParatext "false" @default.
- W3081097499 isRetracted "false" @default.
- W3081097499 magId "3081097499" @default.
- W3081097499 workType "article" @default.