FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210990719> ?p ?o ?g. }

• W4210990719 endingPage "20444" @default.
• W4210990719 startingPage "20432" @default.
• W4210990719 abstract "A learning-based image relighting framework is proposed for automatically changing the lighting conditions of facial images from one lighting source to another. Given only a 2D unseen facial testing image, the framework automatically infers the highlight or shadow areas in the relighted image in accordance with the specific facial characteristics of the input image using a learned non-parametric Markov random field model of the facial appearance correlation between the source and target lighting conditions. The proposed framework first decomposes the input image into its global and local components, where these components relate mainly to the lighting and detailed facial appearance characteristics of the image, respectively. The two components are then processed independently to ease the problem of insufficient training samples and to properly analyze the local contrast, overall lighting direction effects, and personal feature characteristics of the unseen subject. Specifically, the global and local components are processed by a lighting–aware classifier and a personal characteristic–aware classifier, respectively, in order to determine the semantic factors of the facial region. The semantic factors of the facial region are then used to update the Markov random field model of the facial appearance correlation between the source and target lighting conditions and to produce lighting enhancement matrices for the lighting components and facial characteristic components, respectively. Finally, the lighting enhancement matrices are applied to the original decomposition images, which are then integrated to obtain the final relighted result. The experimental results show that the proposed image relighting framework generates vivid and recognizable results despite the scarcity of training samples. Furthermore, the relighted results successfully simulate the individual lighting effects produced by the specific personal characteristics of the input image, such as the nose and cheek shadows. The effectiveness of the proposed framework is demonstrated by means of face verification tests, in which input images taken under side-lighting conditions are transformed to normal lighting conditions and are then matched with a dataset of ground truth images also taken under normal lighting conditions." @default.
• W4210990719 created "2022-02-13" @default.
• W4210990719 creator A5025113833 @default.
• W4210990719 creator A5063924054 @default.
• W4210990719 creator A5066474338 @default.
• W4210990719 date "2022-01-01" @default.
• W4210990719 modified "2023-09-25" @default.
• W4210990719 title "Lighting- and Personal Characteristic-Aware Markov Random Field Model for Facial Image Relighting System" @default.
• W4210990719 cites W2002464721 @default.
• W4210990719 cites W2006793117 @default.
• W4210990719 cites W2059643374 @default.
• W4210990719 cites W2095643100 @default.
• W4210990719 cites W2106395586 @default.
• W4210990719 cites W2108428911 @default.
• W4210990719 cites W2109486640 @default.
• W4210990719 cites W2123921160 @default.
• W4210990719 cites W2127847374 @default.
• W4210990719 cites W2129680231 @default.
• W4210990719 cites W2136407193 @default.
• W4210990719 cites W2275363859 @default.
• W4210990719 cites W2465883194 @default.
• W4210990719 cites W2749568986 @default.
• W4210990719 cites W2767395154 @default.
• W4210990719 cites W2773332582 @default.
• W4210990719 cites W2791694917 @default.
• W4210990719 cites W2808291191 @default.
• W4210990719 cites W2810337759 @default.
• W4210990719 cites W2945361107 @default.
• W4210990719 cites W2962793481 @default.
• W4210990719 cites W2963073614 @default.
• W4210990719 cites W2972003492 @default.
• W4210990719 cites W2979836745 @default.
• W4210990719 cites W2985680131 @default.
• W4210990719 cites W2999903067 @default.
• W4210990719 cites W3009769734 @default.
• W4210990719 cites W3042502878 @default.
• W4210990719 cites W3110182603 @default.
• W4210990719 cites W3134190725 @default.
• W4210990719 doi "https://doi.org/10.1109/access.2022.3150341" @default.
• W4210990719 hasPublicationYear "2022" @default.
• W4210990719 type Work @default.
• W4210990719 citedByCount "0" @default.
• W4210990719 crossrefType "journal-article" @default.
• W4210990719 hasAuthorship W4210990719A5025113833 @default.
• W4210990719 hasAuthorship W4210990719A5063924054 @default.
• W4210990719 hasAuthorship W4210990719A5066474338 @default.
• W4210990719 hasBestOaLocation W42109907191 @default.
• W4210990719 hasConcept C115961682 @default.
• W4210990719 hasConcept C124504099 @default.
• W4210990719 hasConcept C153180895 @default.
• W4210990719 hasConcept C154945302 @default.
• W4210990719 hasConcept C204060014 @default.
• W4210990719 hasConcept C2778045648 @default.
• W4210990719 hasConcept C31972630 @default.
• W4210990719 hasConcept C41008148 @default.
• W4210990719 hasConcept C83248878 @default.
• W4210990719 hasConcept C9417928 @default.
• W4210990719 hasConcept C95623464 @default.
• W4210990719 hasConceptScore W4210990719C115961682 @default.
• W4210990719 hasConceptScore W4210990719C124504099 @default.
• W4210990719 hasConceptScore W4210990719C153180895 @default.
• W4210990719 hasConceptScore W4210990719C154945302 @default.
• W4210990719 hasConceptScore W4210990719C204060014 @default.
• W4210990719 hasConceptScore W4210990719C2778045648 @default.
• W4210990719 hasConceptScore W4210990719C31972630 @default.
• W4210990719 hasConceptScore W4210990719C41008148 @default.
• W4210990719 hasConceptScore W4210990719C83248878 @default.
• W4210990719 hasConceptScore W4210990719C9417928 @default.
• W4210990719 hasConceptScore W4210990719C95623464 @default.
• W4210990719 hasFunder F4320322795 @default.
• W4210990719 hasLocation W42109907191 @default.
• W4210990719 hasOpenAccess W4210990719 @default.
• W4210990719 hasPrimaryLocation W42109907191 @default.
• W4210990719 hasRelatedWork W1972983025 @default.
• W4210990719 hasRelatedWork W2029274405 @default.
• W4210990719 hasRelatedWork W2056731012 @default.
• W4210990719 hasRelatedWork W2083931353 @default.
• W4210990719 hasRelatedWork W2131155723 @default.
• W4210990719 hasRelatedWork W2161229648 @default.
• W4210990719 hasRelatedWork W2165094896 @default.
• W4210990719 hasRelatedWork W2563096758 @default.
• W4210990719 hasRelatedWork W4386053843 @default.
• W4210990719 hasRelatedWork W3158004940 @default.
• W4210990719 hasVolume "10" @default.
• W4210990719 isParatext "false" @default.
• W4210990719 isRetracted "false" @default.
• W4210990719 workType "article" @default.