Matches in SemOpenAlex for { <https://semopenalex.org/work/W2922908764> ?p ?o ?g. }
- W2922908764 abstract "Recent style transfer models have provided promising artistic results. However, given a photograph as a reference style, existing methods are limited by spatial distortions or unrealistic artifacts, which should not happen in real photographs. We introduce a theoretically sound correction to the network architecture that remarkably enhances photorealism and faithfully transfers the style. The key ingredient of our method is wavelet transforms that naturally fits in deep networks. We propose a wavelet corrected transfer based on whitening and coloring transforms (WCT$^2$) that allows features to preserve their structural information and statistical properties of VGG feature space during stylization. This is the first and the only end-to-end model that can stylize a $1024times1024$ resolution image in 4.7 seconds, giving a pleasing and photorealistic quality without any post-processing. Last but not least, our model provides a stable video stylization without temporal constraints. Our code, generated images, and pre-trained models are all available at https://github.com/ClovaAI/WCT2." @default.
- W2922908764 created "2019-04-01" @default.
- W2922908764 creator A5041472021 @default.
- W2922908764 creator A5067167236 @default.
- W2922908764 creator A5073514062 @default.
- W2922908764 creator A5074393185 @default.
- W2922908764 creator A5089933293 @default.
- W2922908764 date "2019-03-23" @default.
- W2922908764 modified "2023-10-16" @default.
- W2922908764 title "Photorealistic Style Transfer via Wavelet Transforms" @default.
- W2922908764 cites W1522301498 @default.
- W2922908764 cites W1579559187 @default.
- W2922908764 cites W1861492603 @default.
- W2922908764 cites W1901129140 @default.
- W2922908764 cites W2050507755 @default.
- W2922908764 cites W2071666219 @default.
- W2922908764 cites W2072072671 @default.
- W2922908764 cites W2108598243 @default.
- W2922908764 cites W2129112648 @default.
- W2922908764 cites W2141015396 @default.
- W2922908764 cites W2147821504 @default.
- W2922908764 cites W2241289505 @default.
- W2922908764 cites W2475287302 @default.
- W2922908764 cites W2489519930 @default.
- W2922908764 cites W2550673061 @default.
- W2922908764 cites W2551161082 @default.
- W2922908764 cites W2603142085 @default.
- W2922908764 cites W2603777577 @default.
- W2922908764 cites W2603909116 @default.
- W2922908764 cites W2607333215 @default.
- W2922908764 cites W2611605760 @default.
- W2922908764 cites W2737081839 @default.
- W2922908764 cites W2777802649 @default.
- W2922908764 cites W2786128974 @default.
- W2922908764 cites W2788095258 @default.
- W2922908764 cites W2795777276 @default.
- W2922908764 cites W2798520250 @default.
- W2922908764 cites W2891364477 @default.
- W2922908764 cites W2895976713 @default.
- W2922908764 cites W2896786907 @default.
- W2922908764 cites W2962772087 @default.
- W2922908764 cites W2962835968 @default.
- W2922908764 cites W2963264220 @default.
- W2922908764 cites W2963392702 @default.
- W2922908764 cites W3136492254 @default.
- W2922908764 doi "https://doi.org/10.48550/arxiv.1903.09760" @default.
- W2922908764 hasPublicationYear "2019" @default.
- W2922908764 type Work @default.
- W2922908764 sameAs 2922908764 @default.
- W2922908764 citedByCount "6" @default.
- W2922908764 countsByYear W29229087642019 @default.
- W2922908764 countsByYear W29229087642020 @default.
- W2922908764 crossrefType "posted-content" @default.
- W2922908764 hasAuthorship W2922908764A5041472021 @default.
- W2922908764 hasAuthorship W2922908764A5067167236 @default.
- W2922908764 hasAuthorship W2922908764A5073514062 @default.
- W2922908764 hasAuthorship W2922908764A5074393185 @default.
- W2922908764 hasAuthorship W2922908764A5089933293 @default.
- W2922908764 hasBestOaLocation W29229087641 @default.
- W2922908764 hasConcept C121684516 @default.
- W2922908764 hasConcept C124952713 @default.
- W2922908764 hasConcept C138885662 @default.
- W2922908764 hasConcept C142362112 @default.
- W2922908764 hasConcept C153180895 @default.
- W2922908764 hasConcept C154945302 @default.
- W2922908764 hasConcept C173608175 @default.
- W2922908764 hasConcept C177264268 @default.
- W2922908764 hasConcept C17744445 @default.
- W2922908764 hasConcept C196216189 @default.
- W2922908764 hasConcept C199360897 @default.
- W2922908764 hasConcept C199539241 @default.
- W2922908764 hasConcept C26517878 @default.
- W2922908764 hasConcept C2776175482 @default.
- W2922908764 hasConcept C2776359362 @default.
- W2922908764 hasConcept C2776401178 @default.
- W2922908764 hasConcept C2776445246 @default.
- W2922908764 hasConcept C2776760102 @default.
- W2922908764 hasConcept C31972630 @default.
- W2922908764 hasConcept C38652104 @default.
- W2922908764 hasConcept C41008148 @default.
- W2922908764 hasConcept C41895202 @default.
- W2922908764 hasConcept C47432892 @default.
- W2922908764 hasConcept C94625758 @default.
- W2922908764 hasConceptScore W2922908764C121684516 @default.
- W2922908764 hasConceptScore W2922908764C124952713 @default.
- W2922908764 hasConceptScore W2922908764C138885662 @default.
- W2922908764 hasConceptScore W2922908764C142362112 @default.
- W2922908764 hasConceptScore W2922908764C153180895 @default.
- W2922908764 hasConceptScore W2922908764C154945302 @default.
- W2922908764 hasConceptScore W2922908764C173608175 @default.
- W2922908764 hasConceptScore W2922908764C177264268 @default.
- W2922908764 hasConceptScore W2922908764C17744445 @default.
- W2922908764 hasConceptScore W2922908764C196216189 @default.
- W2922908764 hasConceptScore W2922908764C199360897 @default.
- W2922908764 hasConceptScore W2922908764C199539241 @default.
- W2922908764 hasConceptScore W2922908764C26517878 @default.
- W2922908764 hasConceptScore W2922908764C2776175482 @default.
- W2922908764 hasConceptScore W2922908764C2776359362 @default.
- W2922908764 hasConceptScore W2922908764C2776401178 @default.
- W2922908764 hasConceptScore W2922908764C2776445246 @default.