FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2889050557> ?p ?o ?g. }

• W2889050557 endingPage "1" @default.
• W2889050557 startingPage "1" @default.
• W2889050557 abstract "As a classic statistical model of 3D facial shape and albedo, 3D Morphable Model (3DMM) is widely used in facial analysis, e.g., model fitting, image synthesis. Conventional 3DMM is learned from a set of 3D face scans with associated well-controlled 2D face images, and represented by two sets of PCA basis functions. Due to the type and amount of training data, as well as, the linear bases, the representation power of 3DMM can be limited. To address these problems, this paper proposes an innovative framework to learn a nonlinear 3DMM model from a large set of in-the-wild face images, without collecting 3D face scans. Specifically, given a face image as input, a network encoder estimates the projection, lighting, shape and albedo parameters. Two decoders serve as the nonlinear 3DMM to map from the shape and albedo parameters to the 3D shape and albedo, respectively. With the projection parameter, lighting, 3D shape, and albedo, a novel analytically-differentiable rendering layer is designed to reconstruct the original input face. The entire network is end-to-end trainable with only weak supervision. We demonstrate the superior representation power of our nonlinear 3DMM over its linear counterpart, and its contribution to face alignment, 3D reconstruction, and face editing." @default.
• W2889050557 created "2018-09-07" @default.
• W2889050557 creator A5014978361 @default.
• W2889050557 creator A5077998492 @default.
• W2889050557 date "2019-01-01" @default.
• W2889050557 modified "2023-10-16" @default.
• W2889050557 title "On Learning 3D Face Morphable Model from In-the-wild Images" @default.
• W2889050557 cites W1499329969 @default.
• W2889050557 cites W1682276745 @default.
• W2889050557 cites W1834627138 @default.
• W2889050557 cites W1919814523 @default.
• W2889050557 cites W1940113235 @default.
• W2889050557 cites W2003706019 @default.
• W2889050557 cites W2004068758 @default.
• W2889050557 cites W2017107803 @default.
• W2889050557 cites W2046571636 @default.
• W2889050557 cites W2059404013 @default.
• W2889050557 cites W2081420403 @default.
• W2889050557 cites W2087007396 @default.
• W2889050557 cites W2105649179 @default.
• W2889050557 cites W2107037917 @default.
• W2889050557 cites W2108428911 @default.
• W2889050557 cites W2115727890 @default.
• W2889050557 cites W2122585444 @default.
• W2889050557 cites W2128409098 @default.
• W2889050557 cites W2135666716 @default.
• W2889050557 cites W2136000821 @default.
• W2889050557 cites W2148457221 @default.
• W2889050557 cites W2149918784 @default.
• W2889050557 cites W2152826865 @default.
• W2889050557 cites W2160126058 @default.
• W2889050557 cites W2166468061 @default.
• W2889050557 cites W2168722300 @default.
• W2889050557 cites W2169635990 @default.
• W2889050557 cites W2180648442 @default.
• W2889050557 cites W2194775991 @default.
• W2889050557 cites W2197128021 @default.
• W2889050557 cites W2214733281 @default.
• W2889050557 cites W2237250383 @default.
• W2889050557 cites W2265959009 @default.
• W2889050557 cites W2284800790 @default.
• W2889050557 cites W2331128040 @default.
• W2889050557 cites W2398381847 @default.
• W2889050557 cites W2431101926 @default.
• W2889050557 cites W2465108587 @default.
• W2889050557 cites W2468336759 @default.
• W2889050557 cites W2486034530 @default.
• W2889050557 cites W2519131448 @default.
• W2889050557 cites W2520331172 @default.
• W2889050557 cites W2546584497 @default.
• W2889050557 cites W2555510177 @default.
• W2889050557 cites W2559821077 @default.
• W2889050557 cites W2560722161 @default.
• W2889050557 cites W2582523095 @default.
• W2889050557 cites W2584229793 @default.
• W2889050557 cites W2599226450 @default.
• W2889050557 cites W2605701576 @default.
• W2889050557 cites W2606794139 @default.
• W2889050557 cites W2607170299 @default.
• W2889050557 cites W2608058963 @default.
• W2889050557 cites W2617561348 @default.
• W2889050557 cites W2737047298 @default.
• W2889050557 cites W2751503239 @default.
• W2889050557 cites W2771328060 @default.
• W2889050557 cites W2798291180 @default.
• W2889050557 cites W2804621595 @default.
• W2889050557 cites W2806379360 @default.
• W2889050557 cites W2810084975 @default.
• W2889050557 cites W2962780596 @default.
• W2889050557 cites W2963100452 @default.
• W2889050557 cites W2963253045 @default.
• W2889050557 cites W2963342110 @default.
• W2889050557 cites W2963480351 @default.
• W2889050557 cites W2963915677 @default.
• W2889050557 cites W2964014798 @default.
• W2889050557 cites W2964309795 @default.
• W2889050557 cites W3104792420 @default.
• W2889050557 doi "https://doi.org/10.1109/tpami.2019.2927975" @default.
• W2889050557 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31329546" @default.
• W2889050557 hasPublicationYear "2019" @default.
• W2889050557 type Work @default.
• W2889050557 sameAs 2889050557 @default.
• W2889050557 citedByCount "82" @default.
• W2889050557 countsByYear W28890505572018 @default.
• W2889050557 countsByYear W28890505572019 @default.
• W2889050557 countsByYear W28890505572020 @default.
• W2889050557 countsByYear W28890505572021 @default.
• W2889050557 countsByYear W28890505572022 @default.
• W2889050557 countsByYear W28890505572023 @default.
• W2889050557 crossrefType "journal-article" @default.
• W2889050557 hasAuthorship W2889050557A5014978361 @default.
• W2889050557 hasAuthorship W2889050557A5077998492 @default.
• W2889050557 hasBestOaLocation W28890505572 @default.
• W2889050557 hasConcept C111919701 @default.
• W2889050557 hasConcept C11413529 @default.
• W2889050557 hasConcept C118505674 @default.
• W2889050557 hasConcept C121332964 @default.
• W2889050557 hasConcept C134306372 @default.

• next