FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896628364> ?p ?o ?g. }

• W2896628364 endingPage "370" @default.
• W2896628364 startingPage "357" @default.
• W2896628364 abstract "In this work, we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that serves as decoder. The core innovation is the differentiable parametric decoder that encapsulates image formation analytically based on a generative model. Our decoder takes as input a code vector with exactly defined semantic meaning that encodes detailed face pose, shape, expression, skin reflectance, and scene illumination. Due to this new way of combining CNN-based with model-based face reconstruction, the CNN-based encoder learns to extract semantically meaningful parameters from a single monocular input image. For the first time, a CNN encoder and an expert-designed generative model can be trained end-to-end in an unsupervised manner, which renders training on very large (unlabeled) real world datasets feasible. The obtained reconstructions compare favorably to current state-of-the-art approaches in terms of quality and richness of representation. This work is an extended version of [1] , where we additionally present a stochastic vertex sampling technique for faster training of our networks, and moreover, we propose and evaluate analysis-by-synthesis and shape-from-shading refinement approaches to achieve a high-fidelity reconstruction." @default.
• W2896628364 created "2018-10-26" @default.
• W2896628364 creator A5005789795 @default.
• W2896628364 creator A5020664641 @default.
• W2896628364 creator A5045111379 @default.
• W2896628364 creator A5046744046 @default.
• W2896628364 creator A5053586057 @default.
• W2896628364 creator A5065380232 @default.
• W2896628364 creator A5075797855 @default.
• W2896628364 date "2020-02-01" @default.
• W2896628364 modified "2023-10-02" @default.
• W2896628364 title "High-Fidelity Monocular Face Reconstruction Based on an Unsupervised Model-Based Face Autoencoder" @default.
• W2896628364 cites W1546200464 @default.
• W2896628364 cites W1834627138 @default.
• W2896628364 cites W1915668717 @default.
• W2896628364 cites W1951319388 @default.
• W2896628364 cites W1976948919 @default.
• W2896628364 cites W1982368100 @default.
• W2896628364 cites W1987875999 @default.
• W2896628364 cites W2017107803 @default.
• W2896628364 cites W2059404013 @default.
• W2896628364 cites W2062712751 @default.
• W2896628364 cites W2063601108 @default.
• W2896628364 cites W2069997605 @default.
• W2896628364 cites W2076017598 @default.
• W2896628364 cites W2083473993 @default.
• W2896628364 cites W2098551034 @default.
• W2896628364 cites W2100495367 @default.
• W2896628364 cites W2102924784 @default.
• W2896628364 cites W2107813907 @default.
• W2896628364 cites W2122007052 @default.
• W2896628364 cites W2129210471 @default.
• W2896628364 cites W2134724684 @default.
• W2896628364 cites W2134862753 @default.
• W2896628364 cites W2136655611 @default.
• W2896628364 cites W2137857332 @default.
• W2896628364 cites W2152826865 @default.
• W2896628364 cites W2153169342 @default.
• W2896628364 cites W2155211928 @default.
• W2896628364 cites W2155893237 @default.
• W2896628364 cites W2165306775 @default.
• W2896628364 cites W2166694921 @default.
• W2896628364 cites W2211242044 @default.
• W2896628364 cites W2234876530 @default.
• W2896628364 cites W2237250383 @default.
• W2896628364 cites W2251810906 @default.
• W2896628364 cites W2467255717 @default.
• W2896628364 cites W2468014222 @default.
• W2896628364 cites W2486034530 @default.
• W2896628364 cites W2489710028 @default.
• W2896628364 cites W2507235960 @default.
• W2896628364 cites W2519131448 @default.
• W2896628364 cites W2519365253 @default.
• W2896628364 cites W2555510177 @default.
• W2896628364 cites W2560535660 @default.
• W2896628364 cites W2582523095 @default.
• W2896628364 cites W2584229793 @default.
• W2896628364 cites W2599226450 @default.
• W2896628364 cites W2605701576 @default.
• W2896628364 cites W2611820369 @default.
• W2896628364 cites W2623464795 @default.
• W2896628364 cites W2748448865 @default.
• W2896628364 cites W2767225062 @default.
• W2896628364 cites W2771328060 @default.
• W2896628364 cites W2798409702 @default.
• W2896628364 cites W2798896170 @default.
• W2896628364 cites W2962714886 @default.
• W2896628364 cites W2962780596 @default.
• W2896628364 cites W2962890008 @default.
• W2896628364 cites W2963092747 @default.
• W2896628364 cites W2963202462 @default.
• W2896628364 cites W2963544488 @default.
• W2896628364 cites W328593463 @default.
• W2896628364 cites W4240240566 @default.
• W2896628364 cites W4244800704 @default.
• W2896628364 doi "https://doi.org/10.1109/tpami.2018.2876842" @default.
• W2896628364 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30334783" @default.
• W2896628364 hasPublicationYear "2020" @default.
• W2896628364 type Work @default.
• W2896628364 sameAs 2896628364 @default.
• W2896628364 citedByCount "43" @default.
• W2896628364 countsByYear W28966283642018 @default.
• W2896628364 countsByYear W28966283642019 @default.
• W2896628364 countsByYear W28966283642020 @default.
• W2896628364 countsByYear W28966283642021 @default.
• W2896628364 countsByYear W28966283642022 @default.
• W2896628364 countsByYear W28966283642023 @default.
• W2896628364 crossrefType "journal-article" @default.
• W2896628364 hasAuthorship W2896628364A5005789795 @default.
• W2896628364 hasAuthorship W2896628364A5020664641 @default.
• W2896628364 hasAuthorship W2896628364A5045111379 @default.
• W2896628364 hasAuthorship W2896628364A5046744046 @default.
• W2896628364 hasAuthorship W2896628364A5053586057 @default.
• W2896628364 hasAuthorship W2896628364A5065380232 @default.
• W2896628364 hasAuthorship W2896628364A5075797855 @default.
• W2896628364 hasBestOaLocation W28966283642 @default.
• W2896628364 hasConcept C101738243 @default.
• W2896628364 hasConcept C108583219 @default.

• next