Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902156735> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2902156735 abstract "Generative Adversarial Networks (GANs) typically learn a distribution of images in a large image dataset, and are then able to generate new images from this distribution. However, each natural image has its own internal statistics, captured by its unique distribution of patches. In this paper we propose an Internal (InGAN) - an image-specific GAN - which trains on a single input image and learns its internal distribution of patches. It is then able to synthesize a plethora of new natural images of significantly different sizes, shapes and aspect-ratios - all with the same internal patch-distribution (same DNA) as the input image. In particular, despite large changes in global size/shape of the image, all elements inside the image maintain their local size/shape. InGAN is fully unsupervised, requiring no additional data other than the input image itself. Once trained on the input image, it can remap the input to any size or shape in a single feedforward pass, while preserving the same internal patch distribution. InGAN provides a unified framework for a variety of tasks, bridging the gap between textures and natural images." @default.
- W2902156735 created "2018-12-11" @default.
- W2902156735 creator A5017456911 @default.
- W2902156735 creator A5041862255 @default.
- W2902156735 creator A5046882196 @default.
- W2902156735 creator A5077200594 @default.
- W2902156735 date "2018-12-01" @default.
- W2902156735 modified "2023-09-26" @default.
- W2902156735 title "Internal Distribution Matching for Natural Image Retargeting." @default.
- W2902156735 cites W1901129140 @default.
- W2902156735 cites W1924619199 @default.
- W2902156735 cites W2018377917 @default.
- W2902156735 cites W2062811295 @default.
- W2902156735 cites W2099471712 @default.
- W2902156735 cites W2115273023 @default.
- W2902156735 cites W2194775991 @default.
- W2902156735 cites W2534320940 @default.
- W2902156735 cites W2535388113 @default.
- W2902156735 cites W2557969682 @default.
- W2902156735 cites W2593414223 @default.
- W2902156735 cites W2801495938 @default.
- W2902156735 cites W2949117887 @default.
- W2902156735 cites W2962793481 @default.
- W2902156735 cites W2963083275 @default.
- W2902156735 cites W2963704386 @default.
- W2902156735 cites W2963800363 @default.
- W2902156735 cites W2963836885 @default.
- W2902156735 cites W2963890275 @default.
- W2902156735 cites W2964121744 @default.
- W2902156735 cites W2964193438 @default.
- W2902156735 hasPublicationYear "2018" @default.
- W2902156735 type Work @default.
- W2902156735 sameAs 2902156735 @default.
- W2902156735 citedByCount "7" @default.
- W2902156735 countsByYear W29021567352019 @default.
- W2902156735 countsByYear W29021567352020 @default.
- W2902156735 countsByYear W29021567352021 @default.
- W2902156735 crossrefType "posted-content" @default.
- W2902156735 hasAuthorship W2902156735A5017456911 @default.
- W2902156735 hasAuthorship W2902156735A5041862255 @default.
- W2902156735 hasAuthorship W2902156735A5046882196 @default.
- W2902156735 hasAuthorship W2902156735A5077200594 @default.
- W2902156735 hasConcept C105795698 @default.
- W2902156735 hasConcept C110121322 @default.
- W2902156735 hasConcept C115961682 @default.
- W2902156735 hasConcept C134306372 @default.
- W2902156735 hasConcept C153180895 @default.
- W2902156735 hasConcept C154945302 @default.
- W2902156735 hasConcept C165064840 @default.
- W2902156735 hasConcept C174348530 @default.
- W2902156735 hasConcept C31258907 @default.
- W2902156735 hasConcept C31972630 @default.
- W2902156735 hasConcept C33923547 @default.
- W2902156735 hasConcept C41008148 @default.
- W2902156735 hasConceptScore W2902156735C105795698 @default.
- W2902156735 hasConceptScore W2902156735C110121322 @default.
- W2902156735 hasConceptScore W2902156735C115961682 @default.
- W2902156735 hasConceptScore W2902156735C134306372 @default.
- W2902156735 hasConceptScore W2902156735C153180895 @default.
- W2902156735 hasConceptScore W2902156735C154945302 @default.
- W2902156735 hasConceptScore W2902156735C165064840 @default.
- W2902156735 hasConceptScore W2902156735C174348530 @default.
- W2902156735 hasConceptScore W2902156735C31258907 @default.
- W2902156735 hasConceptScore W2902156735C31972630 @default.
- W2902156735 hasConceptScore W2902156735C33923547 @default.
- W2902156735 hasConceptScore W2902156735C41008148 @default.
- W2902156735 hasLocation W29021567351 @default.
- W2902156735 hasOpenAccess W2902156735 @default.
- W2902156735 hasPrimaryLocation W29021567351 @default.
- W2902156735 hasRelatedWork W2018377917 @default.
- W2902156735 hasRelatedWork W2097073572 @default.
- W2902156735 hasRelatedWork W2115273023 @default.
- W2902156735 hasRelatedWork W2166554908 @default.
- W2902156735 hasRelatedWork W2557414982 @default.
- W2902156735 hasRelatedWork W2613155248 @default.
- W2902156735 hasRelatedWork W2794224632 @default.
- W2902156735 hasRelatedWork W2912450361 @default.
- W2902156735 hasRelatedWork W2941016780 @default.
- W2902156735 hasRelatedWork W2951811868 @default.
- W2902156735 hasRelatedWork W2962793481 @default.
- W2902156735 hasRelatedWork W2963470893 @default.
- W2902156735 hasRelatedWork W2963704386 @default.
- W2902156735 hasRelatedWork W2963800363 @default.
- W2902156735 hasRelatedWork W2964013315 @default.
- W2902156735 hasRelatedWork W2964309429 @default.
- W2902156735 hasRelatedWork W2982041717 @default.
- W2902156735 hasRelatedWork W2982374186 @default.
- W2902156735 hasRelatedWork W3009014607 @default.
- W2902156735 hasRelatedWork W1550336230 @default.
- W2902156735 isParatext "false" @default.
- W2902156735 isRetracted "false" @default.
- W2902156735 magId "2902156735" @default.
- W2902156735 workType "article" @default.