FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3180195040> ?p ?o ?g. }

• W3180195040 abstract "Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions. While plausible facial details are predicted, the models tend to over-depend on local color appearance and suffer from ambiguous noise. To address such problem, this paper presents a novel Learning to Aggregate and Personalize (LAP) framework for unsupervised robust 3D face modeling. Instead of using controlled environment, the proposed method implicitly disentangles ID-consistent and scene-specific face from unconstrained photo set. Specifically, to learn ID-consistent face, LAP adaptively aggregates intrinsic face factors of an identity based on a novel curriculum learning approach with relaxed consistency loss. To adapt the face for a personalized scene, we propose a novel attribute-refining network to modify ID-consistent face with target attribute and details. Based on the proposed method, we make unsupervised 3D face modeling benefit from meaningful image facial structure and possibly higher resolutions. Extensive experiments on benchmarks show LAP recovers superior or competitive face shape and texture, compared with state-of-the-art (SOTA) methods with or without prior and supervision." @default.
• W3180195040 created "2021-07-19" @default.
• W3180195040 creator A5020842034 @default.
• W3180195040 creator A5023834700 @default.
• W3180195040 creator A5024310850 @default.
• W3180195040 creator A5029021362 @default.
• W3180195040 creator A5032461971 @default.
• W3180195040 creator A5045309022 @default.
• W3180195040 creator A5048411184 @default.
• W3180195040 creator A5062318228 @default.
• W3180195040 creator A5067413001 @default.
• W3180195040 date "2021-06-01" @default.
• W3180195040 modified "2023-09-26" @default.
• W3180195040 title "Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection" @default.
• W3180195040 cites W1567532702 @default.
• W3180195040 cites W1834627138 @default.
• W3180195040 cites W2018727909 @default.
• W3180195040 cites W2051297709 @default.
• W3180195040 cites W2081063977 @default.
• W3180195040 cites W2097365005 @default.
• W3180195040 cites W2107037917 @default.
• W3180195040 cites W2118304946 @default.
• W3180195040 cites W2121314241 @default.
• W3180195040 cites W2133665775 @default.
• W3180195040 cites W2155211928 @default.
• W3180195040 cites W2237250383 @default.
• W3180195040 cites W2296073425 @default.
• W3180195040 cites W2519131448 @default.
• W3180195040 cites W2520331172 @default.
• W3180195040 cites W2555510177 @default.
• W3180195040 cites W2584229793 @default.
• W3180195040 cites W2599226450 @default.
• W3180195040 cites W2605701576 @default.
• W3180195040 cites W2726515241 @default.
• W3180195040 cites W2767225062 @default.
• W3180195040 cites W2771328060 @default.
• W3180195040 cites W2795709097 @default.
• W3180195040 cites W2796822548 @default.
• W3180195040 cites W2807725536 @default.
• W3180195040 cites W2912990735 @default.
• W3180195040 cites W2917887692 @default.
• W3180195040 cites W2945729334 @default.
• W3180195040 cites W2948127555 @default.
• W3180195040 cites W2948303854 @default.
• W3180195040 cites W2962770929 @default.
• W3180195040 cites W2962780596 @default.
• W3180195040 cites W2962860871 @default.
• W3180195040 cites W2962922861 @default.
• W3180195040 cites W2963216120 @default.
• W3180195040 cites W2963527086 @default.
• W3180195040 cites W2963557052 @default.
• W3180195040 cites W2963590054 @default.
• W3180195040 cites W2964014798 @default.
• W3180195040 cites W2964094607 @default.
• W3180195040 cites W2965392395 @default.
• W3180195040 cites W2969985801 @default.
• W3180195040 cites W2970131683 @default.
• W3180195040 cites W2981441786 @default.
• W3180195040 cites W2984006054 @default.
• W3180195040 cites W3000817459 @default.
• W3180195040 cites W3034192160 @default.
• W3180195040 cites W3034431451 @default.
• W3180195040 cites W3034512702 @default.
• W3180195040 cites W3034521057 @default.
• W3180195040 cites W3035174858 @default.
• W3180195040 cites W3035382289 @default.
• W3180195040 cites W3035693354 @default.
• W3180195040 cites W3096509145 @default.
• W3180195040 cites W3097586952 @default.
• W3180195040 cites W3104300620 @default.
• W3180195040 cites W3109317096 @default.
• W3180195040 doi "https://doi.org/10.1109/cvpr46437.2021.01399" @default.
• W3180195040 hasPublicationYear "2021" @default.
• W3180195040 type Work @default.
• W3180195040 sameAs 3180195040 @default.
• W3180195040 citedByCount "11" @default.
• W3180195040 countsByYear W31801950402022 @default.
• W3180195040 countsByYear W31801950402023 @default.
• W3180195040 crossrefType "proceedings-article" @default.
• W3180195040 hasAuthorship W3180195040A5020842034 @default.
• W3180195040 hasAuthorship W3180195040A5023834700 @default.
• W3180195040 hasAuthorship W3180195040A5024310850 @default.
• W3180195040 hasAuthorship W3180195040A5029021362 @default.
• W3180195040 hasAuthorship W3180195040A5032461971 @default.
• W3180195040 hasAuthorship W3180195040A5045309022 @default.
• W3180195040 hasAuthorship W3180195040A5048411184 @default.
• W3180195040 hasAuthorship W3180195040A5062318228 @default.
• W3180195040 hasAuthorship W3180195040A5067413001 @default.
• W3180195040 hasBestOaLocation W31801950402 @default.
• W3180195040 hasConcept C105795698 @default.
• W3180195040 hasConcept C115961682 @default.
• W3180195040 hasConcept C117251300 @default.
• W3180195040 hasConcept C119857082 @default.
• W3180195040 hasConcept C121332964 @default.
• W3180195040 hasConcept C144024400 @default.
• W3180195040 hasConcept C153180895 @default.
• W3180195040 hasConcept C154945302 @default.
• W3180195040 hasConcept C177264268 @default.
• W3180195040 hasConcept C199360897 @default.
• W3180195040 hasConcept C24890656 @default.

• next