Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952808330> ?p ?o ?g. }
- W2952808330 abstract "We introduce InverseFaceNet, a deep convolutional inverse rendering framework for faces that jointly estimates facial pose, shape, expression, reflectance and illumination from a single input image. By estimating all parameters from just a single image, advanced editing possibilities on a single face image, such as appearance editing and relighting, become feasible in real time. Most previous learning-based face reconstruction approaches do not jointly recover all dimensions, or are severely limited in terms of visual quality. In contrast, we propose to recover high-quality facial pose, shape, expression, reflectance and illumination using a deep neural network that is trained using a large, synthetically created training corpus. Our approach builds on a novel loss function that measures model-space similarity directly in parameter space and significantly improves reconstruction accuracy. We further propose a self-supervised bootstrapping process in the network training loop, which iteratively updates the synthetic training corpus to better reflect the distribution of real-world imagery. We demonstrate that this strategy outperforms completely synthetically trained networks. Finally, we show high-quality reconstructions and compare our approach to several state-of-the-art approaches." @default.
- W2952808330 created "2019-06-27" @default.
- W2952808330 creator A5005789795 @default.
- W2952808330 creator A5020664641 @default.
- W2952808330 creator A5036392768 @default.
- W2952808330 creator A5046744046 @default.
- W2952808330 creator A5075797855 @default.
- W2952808330 creator A5090657753 @default.
- W2952808330 date "2017-03-31" @default.
- W2952808330 modified "2023-09-27" @default.
- W2952808330 title "InverseFaceNet: Deep Monocular Inverse Face Rendering" @default.
- W2952808330 cites W125358319 @default.
- W2952808330 cites W1691728462 @default.
- W2952808330 cites W1782590233 @default.
- W2952808330 cites W1834627138 @default.
- W2952808330 cites W1916003155 @default.
- W2952808330 cites W1940113235 @default.
- W2952808330 cites W1961571273 @default.
- W2952808330 cites W1992187125 @default.
- W2952808330 cites W2003706019 @default.
- W2952808330 cites W2004068758 @default.
- W2952808330 cites W2012075579 @default.
- W2952808330 cites W2013871799 @default.
- W2952808330 cites W2017107803 @default.
- W2952808330 cites W2017622341 @default.
- W2952808330 cites W2038891881 @default.
- W2952808330 cites W2063601108 @default.
- W2952808330 cites W2097108975 @default.
- W2952808330 cites W2099478163 @default.
- W2952808330 cites W2117539524 @default.
- W2952808330 cites W2134724684 @default.
- W2952808330 cites W2134862753 @default.
- W2952808330 cites W2152826865 @default.
- W2952808330 cites W2227411572 @default.
- W2952808330 cites W2237250383 @default.
- W2952808330 cites W2398381847 @default.
- W2952808330 cites W2507537916 @default.
- W2952808330 cites W2513385807 @default.
- W2952808330 cites W2514847725 @default.
- W2952808330 cites W2517797371 @default.
- W2952808330 cites W2519131448 @default.
- W2952808330 cites W2522963512 @default.
- W2952808330 cites W2555510177 @default.
- W2952808330 cites W2560012948 @default.
- W2952808330 cites W2584229793 @default.
- W2952808330 cites W2906447902 @default.
- W2952808330 cites W2949125164 @default.
- W2952808330 cites W2949650786 @default.
- W2952808330 cites W2950094539 @default.
- W2952808330 cites W2951365993 @default.
- W2952808330 cites W2951647946 @default.
- W2952808330 cites W2951863354 @default.
- W2952808330 cites W2963474899 @default.
- W2952808330 cites W3106701803 @default.
- W2952808330 cites W6908809 @default.
- W2952808330 doi "https://doi.org/10.48550/arxiv.1703.10956" @default.
- W2952808330 hasPublicationYear "2017" @default.
- W2952808330 type Work @default.
- W2952808330 sameAs 2952808330 @default.
- W2952808330 citedByCount "9" @default.
- W2952808330 countsByYear W29528083302017 @default.
- W2952808330 countsByYear W29528083302018 @default.
- W2952808330 countsByYear W29528083302019 @default.
- W2952808330 crossrefType "posted-content" @default.
- W2952808330 hasAuthorship W2952808330A5005789795 @default.
- W2952808330 hasAuthorship W2952808330A5020664641 @default.
- W2952808330 hasAuthorship W2952808330A5036392768 @default.
- W2952808330 hasAuthorship W2952808330A5046744046 @default.
- W2952808330 hasAuthorship W2952808330A5075797855 @default.
- W2952808330 hasAuthorship W2952808330A5090657753 @default.
- W2952808330 hasBestOaLocation W29528083301 @default.
- W2952808330 hasConcept C108583219 @default.
- W2952808330 hasConcept C144024400 @default.
- W2952808330 hasConcept C153180895 @default.
- W2952808330 hasConcept C154945302 @default.
- W2952808330 hasConcept C205711294 @default.
- W2952808330 hasConcept C2779304628 @default.
- W2952808330 hasConcept C31972630 @default.
- W2952808330 hasConcept C36289849 @default.
- W2952808330 hasConcept C41008148 @default.
- W2952808330 hasConcept C65909025 @default.
- W2952808330 hasConcept C81363708 @default.
- W2952808330 hasConceptScore W2952808330C108583219 @default.
- W2952808330 hasConceptScore W2952808330C144024400 @default.
- W2952808330 hasConceptScore W2952808330C153180895 @default.
- W2952808330 hasConceptScore W2952808330C154945302 @default.
- W2952808330 hasConceptScore W2952808330C205711294 @default.
- W2952808330 hasConceptScore W2952808330C2779304628 @default.
- W2952808330 hasConceptScore W2952808330C31972630 @default.
- W2952808330 hasConceptScore W2952808330C36289849 @default.
- W2952808330 hasConceptScore W2952808330C41008148 @default.
- W2952808330 hasConceptScore W2952808330C65909025 @default.
- W2952808330 hasConceptScore W2952808330C81363708 @default.
- W2952808330 hasLocation W29528083301 @default.
- W2952808330 hasLocation W29528083302 @default.
- W2952808330 hasOpenAccess W2952808330 @default.
- W2952808330 hasPrimaryLocation W29528083301 @default.
- W2952808330 hasRelatedWork W1803059841 @default.
- W2952808330 hasRelatedWork W2138569648 @default.
- W2952808330 hasRelatedWork W2731899572 @default.