Matches in SemOpenAlex for { <https://semopenalex.org/work/W2967836412> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2967836412 endingPage "110357" @default.
- W2967836412 startingPage "110344" @default.
- W2967836412 abstract "Generative adversarial networks (GANs) are used for image enhancement such as single image super-resolution (SISR) and deblurring. The conventional GANs-based image enhancement suffers from two drawbacks that cause a quality degradation due to a loss of detailed information. First, the conventional discriminator network adopts strided convolution layers which cause a reduction in the resolution of the feature map, and thereby resulting in a loss of detailed information. Second, the previous GANs for image enhancement use the feature map of the visual geometry group (VGG) network for generating a content loss, which also causes visual artifacts because the maxpooling layers in the VGG network result in a loss of detailed information. To overcome these two drawbacks, this paper presents a proposal of a new resolution-preserving discriminator network architecture which removes the strided convolution layers, and a new content loss generated from the VGG network without maxpooling layers. The proposed discriminator network is applied to the super-resolution generative adversarial network (SRGAN), which is called a resolution-preserving SRGAN (RPSRGAN). Experimental results show that RPSRGAN generates more realistic super-resolution images than SRGAN does, and consequently, RPSRGAN with the new content loss improves the average peak signal-to-noise ratio (PSNR) by 0.75 dB and 0.32 dB for super-resolution images with the scale factors of 2 and 4, respectively. For deblurring, the visual appearance is also significantly improved, and the average PSNR is increased by 1.54 dB when the proposed discriminator and content loss are applied to the deblurring adversarial network." @default.
- W2967836412 created "2019-08-22" @default.
- W2967836412 creator A5005948302 @default.
- W2967836412 creator A5024723558 @default.
- W2967836412 creator A5039863333 @default.
- W2967836412 creator A5061210941 @default.
- W2967836412 creator A5079207986 @default.
- W2967836412 date "2019-01-01" @default.
- W2967836412 modified "2023-09-27" @default.
- W2967836412 title "Resolution-Preserving Generative Adversarial Networks for Image Enhancement" @default.
- W2967836412 cites W1916935112 @default.
- W2967836412 cites W1930824406 @default.
- W2967836412 cites W1982067089 @default.
- W2967836412 cites W2047920195 @default.
- W2967836412 cites W2117539524 @default.
- W2967836412 cites W2118963448 @default.
- W2967836412 cites W2121058967 @default.
- W2967836412 cites W2121927366 @default.
- W2967836412 cites W2133665775 @default.
- W2967836412 cites W2150081556 @default.
- W2967836412 cites W2194775991 @default.
- W2967836412 cites W2242218935 @default.
- W2967836412 cites W2300657047 @default.
- W2967836412 cites W2476548250 @default.
- W2967836412 cites W2560533888 @default.
- W2967836412 cites W2579111433 @default.
- W2967836412 cites W2741137940 @default.
- W2967836412 cites W2895240252 @default.
- W2967836412 cites W2920973181 @default.
- W2967836412 cites W2939571759 @default.
- W2967836412 cites W2963037581 @default.
- W2967836412 cites W2963073614 @default.
- W2967836412 cites W2963372104 @default.
- W2967836412 cites W2963470893 @default.
- W2967836412 doi "https://doi.org/10.1109/access.2019.2934320" @default.
- W2967836412 hasPublicationYear "2019" @default.
- W2967836412 type Work @default.
- W2967836412 sameAs 2967836412 @default.
- W2967836412 citedByCount "12" @default.
- W2967836412 countsByYear W29678364122019 @default.
- W2967836412 countsByYear W29678364122020 @default.
- W2967836412 countsByYear W29678364122021 @default.
- W2967836412 countsByYear W29678364122022 @default.
- W2967836412 crossrefType "journal-article" @default.
- W2967836412 hasAuthorship W2967836412A5005948302 @default.
- W2967836412 hasAuthorship W2967836412A5024723558 @default.
- W2967836412 hasAuthorship W2967836412A5039863333 @default.
- W2967836412 hasAuthorship W2967836412A5061210941 @default.
- W2967836412 hasAuthorship W2967836412A5079207986 @default.
- W2967836412 hasBestOaLocation W29678364121 @default.
- W2967836412 hasConcept C115961682 @default.
- W2967836412 hasConcept C138268822 @default.
- W2967836412 hasConcept C153180895 @default.
- W2967836412 hasConcept C154945302 @default.
- W2967836412 hasConcept C2988773926 @default.
- W2967836412 hasConcept C31972630 @default.
- W2967836412 hasConcept C37736160 @default.
- W2967836412 hasConcept C39890363 @default.
- W2967836412 hasConcept C41008148 @default.
- W2967836412 hasConceptScore W2967836412C115961682 @default.
- W2967836412 hasConceptScore W2967836412C138268822 @default.
- W2967836412 hasConceptScore W2967836412C153180895 @default.
- W2967836412 hasConceptScore W2967836412C154945302 @default.
- W2967836412 hasConceptScore W2967836412C2988773926 @default.
- W2967836412 hasConceptScore W2967836412C31972630 @default.
- W2967836412 hasConceptScore W2967836412C37736160 @default.
- W2967836412 hasConceptScore W2967836412C39890363 @default.
- W2967836412 hasConceptScore W2967836412C41008148 @default.
- W2967836412 hasFunder F4320322382 @default.
- W2967836412 hasLocation W29678364121 @default.
- W2967836412 hasOpenAccess W2967836412 @default.
- W2967836412 hasPrimaryLocation W29678364121 @default.
- W2967836412 hasRelatedWork W2944432393 @default.
- W2967836412 hasRelatedWork W2982455199 @default.
- W2967836412 hasRelatedWork W3022669721 @default.
- W2967836412 hasRelatedWork W3024390022 @default.
- W2967836412 hasRelatedWork W3137494590 @default.
- W2967836412 hasRelatedWork W3142157510 @default.
- W2967836412 hasRelatedWork W3156291593 @default.
- W2967836412 hasRelatedWork W3178813832 @default.
- W2967836412 hasRelatedWork W4206598283 @default.
- W2967836412 hasRelatedWork W4313479464 @default.
- W2967836412 hasVolume "7" @default.
- W2967836412 isParatext "false" @default.
- W2967836412 isRetracted "false" @default.
- W2967836412 magId "2967836412" @default.
- W2967836412 workType "article" @default.