Matches in SemOpenAlex for { <https://semopenalex.org/work/W2035308043> ?p ?o ?g. }
- W2035308043 abstract "Example-based texture synthesis (ETS) has been widely used to generate high quality textures of desired sizes from a small example. However, not all textures are equally well reproducible that way. We predict how synthesizable a particular texture is by ETS. We introduce a dataset (21, 302 textures) of which all images have been annotated in terms of their synthesizability. We design a set of texture features, such as 'textureness', homogeneity, repetitiveness, and irregularity, and train a predictor using these features on the data collection. This work is the first attempt to quantify this image property, and we find that texture synthesizability can be learned and predicted. We use this insight to trim images to parts that are more synthesizable. Also we suggest which texture synthesis method is best suited to synthesise a given texture. Our approach can be seen as 'winner-uses-all': picking one method among several alternatives, ending up with an overall superior ETS method. Such strategy could also be considered for other vision tasks: rather than building an even stronger method, choose from existing methods based on some simple preprocessing." @default.
- W2035308043 created "2016-06-24" @default.
- W2035308043 creator A5001254143 @default.
- W2035308043 creator A5011444017 @default.
- W2035308043 creator A5078838951 @default.
- W2035308043 date "2014-06-01" @default.
- W2035308043 modified "2023-10-17" @default.
- W2035308043 title "The Synthesizability of Texture Examples" @default.
- W2035308043 cites W1484228140 @default.
- W2035308043 cites W1490632837 @default.
- W2035308043 cites W1566135517 @default.
- W2035308043 cites W1966845411 @default.
- W2035308043 cites W1967577110 @default.
- W2035308043 cites W1977364474 @default.
- W2035308043 cites W1978563198 @default.
- W2035308043 cites W1999360130 @default.
- W2035308043 cites W2009627211 @default.
- W2035308043 cites W2010269264 @default.
- W2035308043 cites W2026418062 @default.
- W2035308043 cites W2038836824 @default.
- W2035308043 cites W2042371054 @default.
- W2035308043 cites W2077786999 @default.
- W2035308043 cites W2083866943 @default.
- W2035308043 cites W2089366864 @default.
- W2035308043 cites W2093224205 @default.
- W2035308043 cites W2099544729 @default.
- W2035308043 cites W2099835437 @default.
- W2035308043 cites W2116013899 @default.
- W2035308043 cites W2117311720 @default.
- W2035308043 cites W2125148312 @default.
- W2035308043 cites W2126833203 @default.
- W2035308043 cites W2127006916 @default.
- W2035308043 cites W2140207570 @default.
- W2035308043 cites W2143516773 @default.
- W2035308043 cites W2144170305 @default.
- W2035308043 cites W2150920547 @default.
- W2035308043 cites W2151009539 @default.
- W2035308043 cites W2152548630 @default.
- W2035308043 cites W2152942156 @default.
- W2035308043 cites W2162915993 @default.
- W2035308043 cites W2163352848 @default.
- W2035308043 cites W2911964244 @default.
- W2035308043 cites W4205666164 @default.
- W2035308043 cites W4255662947 @default.
- W2035308043 cites W4255747608 @default.
- W2035308043 doi "https://doi.org/10.1109/cvpr.2014.387" @default.
- W2035308043 hasPublicationYear "2014" @default.
- W2035308043 type Work @default.
- W2035308043 sameAs 2035308043 @default.
- W2035308043 citedByCount "29" @default.
- W2035308043 countsByYear W20353080432014 @default.
- W2035308043 countsByYear W20353080432015 @default.
- W2035308043 countsByYear W20353080432016 @default.
- W2035308043 countsByYear W20353080432017 @default.
- W2035308043 countsByYear W20353080432018 @default.
- W2035308043 countsByYear W20353080432019 @default.
- W2035308043 countsByYear W20353080432020 @default.
- W2035308043 countsByYear W20353080432021 @default.
- W2035308043 countsByYear W20353080432022 @default.
- W2035308043 crossrefType "proceedings-article" @default.
- W2035308043 hasAuthorship W2035308043A5001254143 @default.
- W2035308043 hasAuthorship W2035308043A5011444017 @default.
- W2035308043 hasAuthorship W2035308043A5078838951 @default.
- W2035308043 hasBestOaLocation W20353080432 @default.
- W2035308043 hasConcept C111472728 @default.
- W2035308043 hasConcept C111919701 @default.
- W2035308043 hasConcept C115961682 @default.
- W2035308043 hasConcept C138885662 @default.
- W2035308043 hasConcept C144743038 @default.
- W2035308043 hasConcept C153180895 @default.
- W2035308043 hasConcept C154945302 @default.
- W2035308043 hasConcept C177264268 @default.
- W2035308043 hasConcept C189950617 @default.
- W2035308043 hasConcept C199360897 @default.
- W2035308043 hasConcept C207183524 @default.
- W2035308043 hasConcept C2781195486 @default.
- W2035308043 hasConcept C31972630 @default.
- W2035308043 hasConcept C34736171 @default.
- W2035308043 hasConcept C41008148 @default.
- W2035308043 hasConcept C50494287 @default.
- W2035308043 hasConcept C54243161 @default.
- W2035308043 hasConcept C63099799 @default.
- W2035308043 hasConcept C88611116 @default.
- W2035308043 hasConcept C9417928 @default.
- W2035308043 hasConceptScore W2035308043C111472728 @default.
- W2035308043 hasConceptScore W2035308043C111919701 @default.
- W2035308043 hasConceptScore W2035308043C115961682 @default.
- W2035308043 hasConceptScore W2035308043C138885662 @default.
- W2035308043 hasConceptScore W2035308043C144743038 @default.
- W2035308043 hasConceptScore W2035308043C153180895 @default.
- W2035308043 hasConceptScore W2035308043C154945302 @default.
- W2035308043 hasConceptScore W2035308043C177264268 @default.
- W2035308043 hasConceptScore W2035308043C189950617 @default.
- W2035308043 hasConceptScore W2035308043C199360897 @default.
- W2035308043 hasConceptScore W2035308043C207183524 @default.
- W2035308043 hasConceptScore W2035308043C2781195486 @default.
- W2035308043 hasConceptScore W2035308043C31972630 @default.
- W2035308043 hasConceptScore W2035308043C34736171 @default.
- W2035308043 hasConceptScore W2035308043C41008148 @default.
- W2035308043 hasConceptScore W2035308043C50494287 @default.