Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949274655> ?p ?o ?g. }
- W2949274655 abstract "Recent advances in generative adversarial networks (GANs) have shown great potentials in realistic image synthesis whereas most existing works address synthesis realism in either appearance space or geometry space but few in both. This paper presents an innovative Spatial Fusion GAN (SF-GAN) that combines a geometry synthesizer and an appearance synthesizer to achieve synthesis realism in both geometry and appearance spaces. The geometry synthesizer learns contextual geometries of background images and transforms and places foreground objects into the background images unanimously. The appearance synthesizer adjusts the color, brightness and styles of the foreground objects and embeds them into background images harmoniously, where a guided filter is introduced for detail preserving. The two synthesizers are inter-connected as mutual references which can be trained end-to-end without supervision. The SF-GAN has been evaluated in two tasks: (1) realistic scene text image synthesis for training better recognition models; (2) glass and hat wearing for realistic matching glasses and hats with real portraits. Qualitative and quantitative comparisons with the state-of-the-art demonstrate the superiority of the proposed SF-GAN." @default.
- W2949274655 created "2019-06-27" @default.
- W2949274655 creator A5015639955 @default.
- W2949274655 creator A5023507910 @default.
- W2949274655 creator A5064046791 @default.
- W2949274655 date "2018-12-14" @default.
- W2949274655 modified "2023-09-23" @default.
- W2949274655 title "Spatial Fusion GAN for Image Synthesis" @default.
- W2949274655 cites W1491389626 @default.
- W2949274655 cites W1545189828 @default.
- W2949274655 cites W1591870335 @default.
- W2949274655 cites W1710476689 @default.
- W2949274655 cites W1834627138 @default.
- W2949274655 cites W1950149599 @default.
- W2949274655 cites W1971822075 @default.
- W2949274655 cites W1981283549 @default.
- W2949274655 cites W1987133051 @default.
- W2949274655 cites W1998042868 @default.
- W2949274655 cites W2008806374 @default.
- W2949274655 cites W2070604790 @default.
- W2949274655 cites W2116702374 @default.
- W2949274655 cites W2125389028 @default.
- W2949274655 cites W2128409098 @default.
- W2949274655 cites W2146835493 @default.
- W2949274655 cites W2153182373 @default.
- W2949274655 cites W2161918714 @default.
- W2949274655 cites W2231495490 @default.
- W2949274655 cites W2277595631 @default.
- W2949274655 cites W2291143146 @default.
- W2949274655 cites W2315410813 @default.
- W2949274655 cites W2343052201 @default.
- W2949274655 cites W2397830550 @default.
- W2949274655 cites W2487365028 @default.
- W2949274655 cites W2532759528 @default.
- W2949274655 cites W2564591810 @default.
- W2949274655 cites W2592101326 @default.
- W2949274655 cites W2602234016 @default.
- W2949274655 cites W2604130399 @default.
- W2949274655 cites W2739748921 @default.
- W2949274655 cites W2795619303 @default.
- W2949274655 cites W2797244927 @default.
- W2949274655 cites W2810983211 @default.
- W2949274655 cites W2831607544 @default.
- W2949274655 cites W2873558679 @default.
- W2949274655 cites W2885221386 @default.
- W2949274655 cites W2911919580 @default.
- W2949274655 cites W2939574635 @default.
- W2949274655 cites W2949907962 @default.
- W2949274655 cites W2962737447 @default.
- W2949274655 cites W2962793481 @default.
- W2949274655 cites W2962808524 @default.
- W2949274655 cites W2962947361 @default.
- W2949274655 cites W2963073614 @default.
- W2949274655 cites W2963222130 @default.
- W2949274655 cites W2963226019 @default.
- W2949274655 cites W2963271314 @default.
- W2949274655 cites W2963684088 @default.
- W2949274655 cites W2963709863 @default.
- W2949274655 cites W2963712589 @default.
- W2949274655 cites W2963887671 @default.
- W2949274655 cites W2964024144 @default.
- W2949274655 cites W2964082390 @default.
- W2949274655 cites W3148140980 @default.
- W2949274655 cites W648143168 @default.
- W2949274655 doi "https://doi.org/10.48550/arxiv.1812.05840" @default.
- W2949274655 hasPublicationYear "2018" @default.
- W2949274655 type Work @default.
- W2949274655 sameAs 2949274655 @default.
- W2949274655 citedByCount "6" @default.
- W2949274655 countsByYear W29492746552019 @default.
- W2949274655 countsByYear W29492746552020 @default.
- W2949274655 countsByYear W29492746552021 @default.
- W2949274655 crossrefType "posted-content" @default.
- W2949274655 hasAuthorship W2949274655A5015639955 @default.
- W2949274655 hasAuthorship W2949274655A5023507910 @default.
- W2949274655 hasAuthorship W2949274655A5064046791 @default.
- W2949274655 hasBestOaLocation W29492746551 @default.
- W2949274655 hasConcept C105795698 @default.
- W2949274655 hasConcept C106131492 @default.
- W2949274655 hasConcept C111919701 @default.
- W2949274655 hasConcept C115961682 @default.
- W2949274655 hasConcept C154945302 @default.
- W2949274655 hasConcept C165064840 @default.
- W2949274655 hasConcept C2778572836 @default.
- W2949274655 hasConcept C2781238097 @default.
- W2949274655 hasConcept C2989087649 @default.
- W2949274655 hasConcept C31972630 @default.
- W2949274655 hasConcept C33923547 @default.
- W2949274655 hasConcept C41008148 @default.
- W2949274655 hasConcept C50494287 @default.
- W2949274655 hasConcept C63099799 @default.
- W2949274655 hasConcept C9417928 @default.
- W2949274655 hasConceptScore W2949274655C105795698 @default.
- W2949274655 hasConceptScore W2949274655C106131492 @default.
- W2949274655 hasConceptScore W2949274655C111919701 @default.
- W2949274655 hasConceptScore W2949274655C115961682 @default.
- W2949274655 hasConceptScore W2949274655C154945302 @default.
- W2949274655 hasConceptScore W2949274655C165064840 @default.
- W2949274655 hasConceptScore W2949274655C2778572836 @default.
- W2949274655 hasConceptScore W2949274655C2781238097 @default.