Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313002164> ?p ?o ?g. }
- W4313002164 endingPage "439" @default.
- W4313002164 startingPage "423" @default.
- W4313002164 abstract "We present a deep neural network for removing undesirable shading features from an unconstrained portrait image, recovering the underlying texture. Our training scheme incorporates three regularization strategies: masked loss, to emphasize high-frequency shading features; soft-shadow loss, which improves sensitivity to subtle changes in lighting; and shading-offset estimation, to supervise separation of shading and texture. Our method demonstrates improved delighting quality and generalization when compared with the state-of-the-art. We further demonstrate how our delighting method can enhance the performance of light-sensitive computer vision tasks such as face relighting and semantic parsing, allowing them to handle extreme lighting conditions." @default.
- W4313002164 created "2023-01-05" @default.
- W4313002164 creator A5037698938 @default.
- W4313002164 creator A5037956568 @default.
- W4313002164 creator A5048022062 @default.
- W4313002164 creator A5060498631 @default.
- W4313002164 date "2022-01-01" @default.
- W4313002164 modified "2023-09-25" @default.
- W4313002164 title "Deep Portrait Delighting" @default.
- W4313002164 cites W1550922062 @default.
- W4313002164 cites W1677182931 @default.
- W4313002164 cites W1901129140 @default.
- W4313002164 cites W2002464721 @default.
- W4313002164 cites W2067425370 @default.
- W4313002164 cites W2088442775 @default.
- W4313002164 cites W2108428911 @default.
- W4313002164 cites W2108598243 @default.
- W4313002164 cites W2123921160 @default.
- W4313002164 cites W2125188192 @default.
- W4313002164 cites W2125874614 @default.
- W4313002164 cites W2133665775 @default.
- W4313002164 cites W2151976365 @default.
- W4313002164 cites W2235136907 @default.
- W4313002164 cites W2237250383 @default.
- W4313002164 cites W2331128040 @default.
- W4313002164 cites W2593414223 @default.
- W4313002164 cites W2607170299 @default.
- W4313002164 cites W2886934227 @default.
- W4313002164 cites W2908841923 @default.
- W4313002164 cites W2912990735 @default.
- W4313002164 cites W2942551262 @default.
- W4313002164 cites W2962785568 @default.
- W4313002164 cites W2964094607 @default.
- W4313002164 cites W2979836745 @default.
- W4313002164 cites W2985680131 @default.
- W4313002164 cites W2988112387 @default.
- W4313002164 cites W3034192160 @default.
- W4313002164 cites W3034371424 @default.
- W4313002164 cites W3034521057 @default.
- W4313002164 cites W3034868405 @default.
- W4313002164 cites W3048401767 @default.
- W4313002164 cites W3082169377 @default.
- W4313002164 cites W3099362367 @default.
- W4313002164 cites W3159647175 @default.
- W4313002164 cites W3164455552 @default.
- W4313002164 cites W3173947738 @default.
- W4313002164 cites W3174001578 @default.
- W4313002164 cites W4285124635 @default.
- W4313002164 cites W4289076055 @default.
- W4313002164 cites W3202077208 @default.
- W4313002164 doi "https://doi.org/10.1007/978-3-031-19787-1_24" @default.
- W4313002164 hasPublicationYear "2022" @default.
- W4313002164 type Work @default.
- W4313002164 citedByCount "1" @default.
- W4313002164 countsByYear W43130021642023 @default.
- W4313002164 crossrefType "book-chapter" @default.
- W4313002164 hasAuthorship W4313002164A5037698938 @default.
- W4313002164 hasAuthorship W4313002164A5037956568 @default.
- W4313002164 hasAuthorship W4313002164A5048022062 @default.
- W4313002164 hasAuthorship W4313002164A5060498631 @default.
- W4313002164 hasBestOaLocation W43130021642 @default.
- W4313002164 hasConcept C117797892 @default.
- W4313002164 hasConcept C121684516 @default.
- W4313002164 hasConcept C154945302 @default.
- W4313002164 hasConcept C15744967 @default.
- W4313002164 hasConcept C175291020 @default.
- W4313002164 hasConcept C177515723 @default.
- W4313002164 hasConcept C186644900 @default.
- W4313002164 hasConcept C199360897 @default.
- W4313002164 hasConcept C2776135515 @default.
- W4313002164 hasConcept C31972630 @default.
- W4313002164 hasConcept C41008148 @default.
- W4313002164 hasConcept C542102704 @default.
- W4313002164 hasConceptScore W4313002164C117797892 @default.
- W4313002164 hasConceptScore W4313002164C121684516 @default.
- W4313002164 hasConceptScore W4313002164C154945302 @default.
- W4313002164 hasConceptScore W4313002164C15744967 @default.
- W4313002164 hasConceptScore W4313002164C175291020 @default.
- W4313002164 hasConceptScore W4313002164C177515723 @default.
- W4313002164 hasConceptScore W4313002164C186644900 @default.
- W4313002164 hasConceptScore W4313002164C199360897 @default.
- W4313002164 hasConceptScore W4313002164C2776135515 @default.
- W4313002164 hasConceptScore W4313002164C31972630 @default.
- W4313002164 hasConceptScore W4313002164C41008148 @default.
- W4313002164 hasConceptScore W4313002164C542102704 @default.
- W4313002164 hasLocation W43130021641 @default.
- W4313002164 hasLocation W43130021642 @default.
- W4313002164 hasOpenAccess W4313002164 @default.
- W4313002164 hasPrimaryLocation W43130021641 @default.
- W4313002164 hasRelatedWork W1497780831 @default.
- W4313002164 hasRelatedWork W1999949837 @default.
- W4313002164 hasRelatedWork W2034462085 @default.
- W4313002164 hasRelatedWork W2041408572 @default.
- W4313002164 hasRelatedWork W2096492340 @default.
- W4313002164 hasRelatedWork W2317337758 @default.
- W4313002164 hasRelatedWork W2357262985 @default.
- W4313002164 hasRelatedWork W3006419044 @default.
- W4313002164 hasRelatedWork W3014708372 @default.