Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387197019> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4387197019 endingPage "1" @default.
- W4387197019 startingPage "1" @default.
- W4387197019 abstract "Image harmonization aims to address inharmony between the foreground and background of composite images. Current methods mainly adopt the encoder-decoder reconstruction architecture, which restricts their application to high-resolution images due to heavy resource cost. Inspired by Photoshop, whether we can leverage some adjustment tools to apply on composite images to generate harmonized ones. This paper gives an answer yes, and explores a new viewpoint to address image harmonization problem by lookup tables (LUTs) rather than reconstruct full images, which saves a lot of memory. Specifically, a deep model is utilized to encode the down-sampled version of the input image as style-relevant weights to fuse multiple basic LUTs into image-adaptive ones, which are employed to transform the global color of the foreground in source high-resolution composite image to be harmonious with the background. Besides, a spatial attention module is applied to learn the spatial map for revising preliminary LUTs transformation as well as raising the local spatial awareness of the image-adaptive LUTs. Extensive experiments show that our method achieves competitive performance both qualitatively and quantitatively with a smaller model size." @default.
- W4387197019 created "2023-09-30" @default.
- W4387197019 creator A5002685440 @default.
- W4387197019 creator A5003233865 @default.
- W4387197019 creator A5007496002 @default.
- W4387197019 creator A5070757760 @default.
- W4387197019 creator A5018173125 @default.
- W4387197019 date "2023-01-01" @default.
- W4387197019 modified "2023-10-14" @default.
- W4387197019 title "Learning Image-Adaptive Lookup Tables With Spatial Awareness for Image Harmonization" @default.
- W4387197019 doi "https://doi.org/10.1109/tce.2023.3320662" @default.
- W4387197019 hasPublicationYear "2023" @default.
- W4387197019 type Work @default.
- W4387197019 citedByCount "0" @default.
- W4387197019 crossrefType "journal-article" @default.
- W4387197019 hasAuthorship W4387197019A5002685440 @default.
- W4387197019 hasAuthorship W4387197019A5003233865 @default.
- W4387197019 hasAuthorship W4387197019A5007496002 @default.
- W4387197019 hasAuthorship W4387197019A5018173125 @default.
- W4387197019 hasAuthorship W4387197019A5070757760 @default.
- W4387197019 hasConcept C115961682 @default.
- W4387197019 hasConcept C134835016 @default.
- W4387197019 hasConcept C154945302 @default.
- W4387197019 hasConcept C199360897 @default.
- W4387197019 hasConcept C205372480 @default.
- W4387197019 hasConcept C31972630 @default.
- W4387197019 hasConcept C41008148 @default.
- W4387197019 hasConcept C78087231 @default.
- W4387197019 hasConceptScore W4387197019C115961682 @default.
- W4387197019 hasConceptScore W4387197019C134835016 @default.
- W4387197019 hasConceptScore W4387197019C154945302 @default.
- W4387197019 hasConceptScore W4387197019C199360897 @default.
- W4387197019 hasConceptScore W4387197019C205372480 @default.
- W4387197019 hasConceptScore W4387197019C31972630 @default.
- W4387197019 hasConceptScore W4387197019C41008148 @default.
- W4387197019 hasConceptScore W4387197019C78087231 @default.
- W4387197019 hasFunder F4320326705 @default.
- W4387197019 hasLocation W43871970191 @default.
- W4387197019 hasOpenAccess W4387197019 @default.
- W4387197019 hasPrimaryLocation W43871970191 @default.
- W4387197019 hasRelatedWork W1604511055 @default.
- W4387197019 hasRelatedWork W2017573694 @default.
- W4387197019 hasRelatedWork W2026847083 @default.
- W4387197019 hasRelatedWork W2130228941 @default.
- W4387197019 hasRelatedWork W2147047527 @default.
- W4387197019 hasRelatedWork W2161229648 @default.
- W4387197019 hasRelatedWork W2164918837 @default.
- W4387197019 hasRelatedWork W2167088131 @default.
- W4387197019 hasRelatedWork W2940142652 @default.
- W4387197019 hasRelatedWork W2993674027 @default.
- W4387197019 isParatext "false" @default.
- W4387197019 isRetracted "false" @default.
- W4387197019 workType "article" @default.