FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3108361452> ?p ?o ?g. }

• W3108361452 endingPage "169" @default.
• W3108361452 startingPage "154" @default.
• W3108361452 abstract "We present a self-supervised learning approach to learning monocular 3D face reconstruction with a pose guidance network (PGN). First, we unveil the bottleneck of pose estimation in prior parametric 3D face learning methods, and propose to utilize 3D face landmarks for estimating pose parameters. With our specially designed PGN, our model can learn from both faces with fully labeled 3D landmarks and unlimited unlabeled in-the-wild face images. Our network is further augmented with a self-supervised learning scheme, which exploits face geometry information embedded in multiple frames of the same person, to alleviate the ill-posed nature of regressing 3D face geometry from a single image. These three insights yield a single approach that combines the complementary strengths of parametric model learning and data-driven learning techniques. We conduct a rigorous evaluation on the challenging AFLW2000-3D, Florence and FaceWarehouse datasets, and show that our method outperforms the state-of-the-art for all metrics." @default.
• W3108361452 created "2020-12-07" @default.
• W3108361452 creator A5012394408 @default.
• W3108361452 creator A5039977782 @default.
• W3108361452 creator A5042251906 @default.
• W3108361452 creator A5046330465 @default.
• W3108361452 creator A5069195306 @default.
• W3108361452 date "2021-01-01" @default.
• W3108361452 modified "2023-10-13" @default.
• W3108361452 title "Learning 3D Face Reconstruction with a Pose Guidance Network" @default.
• W3108361452 cites W1834627138 @default.
• W3108361452 cites W185671411 @default.
• W3108361452 cites W1946919140 @default.
• W3108361452 cites W2012885984 @default.
• W3108361452 cites W2038891881 @default.
• W3108361452 cites W2087007396 @default.
• W3108361452 cites W2107037917 @default.
• W3108361452 cites W2160126058 @default.
• W3108361452 cites W2237250383 @default.
• W3108361452 cites W2251810906 @default.
• W3108361452 cites W2301937176 @default.
• W3108361452 cites W2339268922 @default.
• W3108361452 cites W2464650832 @default.
• W3108361452 cites W2546505780 @default.
• W3108361452 cites W2584229793 @default.
• W3108361452 cites W2599226450 @default.
• W3108361452 cites W2604672468 @default.
• W3108361452 cites W2605701576 @default.
• W3108361452 cites W2724314443 @default.
• W3108361452 cites W2771328060 @default.
• W3108361452 cites W2796822548 @default.
• W3108361452 cites W2798291180 @default.
• W3108361452 cites W2798896170 @default.
• W3108361452 cites W2806379360 @default.
• W3108361452 cites W2902836694 @default.
• W3108361452 cites W2903334941 @default.
• W3108361452 cites W2904340070 @default.
• W3108361452 cites W2912817214 @default.
• W3108361452 cites W2912990735 @default.
• W3108361452 cites W2945729334 @default.
• W3108361452 cites W2962860871 @default.
• W3108361452 cites W2963202462 @default.
• W3108361452 cites W2963253045 @default.
• W3108361452 cites W2963342110 @default.
• W3108361452 cites W2963480351 @default.
• W3108361452 cites W2964014798 @default.
• W3108361452 cites W2964176417 @default.
• W3108361452 cites W2965115183 @default.
• W3108361452 cites W2970131683 @default.
• W3108361452 cites W3104792420 @default.
• W3108361452 doi "https://doi.org/10.1007/978-3-030-69541-5_10" @default.
• W3108361452 hasPublicationYear "2021" @default.
• W3108361452 type Work @default.
• W3108361452 sameAs 3108361452 @default.
• W3108361452 citedByCount "0" @default.
• W3108361452 crossrefType "book-chapter" @default.
• W3108361452 hasAuthorship W3108361452A5012394408 @default.
• W3108361452 hasAuthorship W3108361452A5039977782 @default.
• W3108361452 hasAuthorship W3108361452A5042251906 @default.
• W3108361452 hasAuthorship W3108361452A5046330465 @default.
• W3108361452 hasAuthorship W3108361452A5069195306 @default.
• W3108361452 hasBestOaLocation W31083614522 @default.
• W3108361452 hasConcept C105795698 @default.
• W3108361452 hasConcept C108583219 @default.
• W3108361452 hasConcept C117251300 @default.
• W3108361452 hasConcept C119857082 @default.
• W3108361452 hasConcept C144024400 @default.
• W3108361452 hasConcept C149635348 @default.
• W3108361452 hasConcept C153180895 @default.
• W3108361452 hasConcept C154945302 @default.
• W3108361452 hasConcept C165696696 @default.
• W3108361452 hasConcept C24574437 @default.
• W3108361452 hasConcept C2779304628 @default.
• W3108361452 hasConcept C2780513914 @default.
• W3108361452 hasConcept C31972630 @default.
• W3108361452 hasConcept C33923547 @default.
• W3108361452 hasConcept C36289849 @default.
• W3108361452 hasConcept C38652104 @default.
• W3108361452 hasConcept C41008148 @default.
• W3108361452 hasConcept C52102323 @default.
• W3108361452 hasConcept C65909025 @default.
• W3108361452 hasConceptScore W3108361452C105795698 @default.
• W3108361452 hasConceptScore W3108361452C108583219 @default.
• W3108361452 hasConceptScore W3108361452C117251300 @default.
• W3108361452 hasConceptScore W3108361452C119857082 @default.
• W3108361452 hasConceptScore W3108361452C144024400 @default.
• W3108361452 hasConceptScore W3108361452C149635348 @default.
• W3108361452 hasConceptScore W3108361452C153180895 @default.
• W3108361452 hasConceptScore W3108361452C154945302 @default.
• W3108361452 hasConceptScore W3108361452C165696696 @default.
• W3108361452 hasConceptScore W3108361452C24574437 @default.
• W3108361452 hasConceptScore W3108361452C2779304628 @default.
• W3108361452 hasConceptScore W3108361452C2780513914 @default.
• W3108361452 hasConceptScore W3108361452C31972630 @default.
• W3108361452 hasConceptScore W3108361452C33923547 @default.
• W3108361452 hasConceptScore W3108361452C36289849 @default.
• W3108361452 hasConceptScore W3108361452C38652104 @default.
• W3108361452 hasConceptScore W3108361452C41008148 @default.

• next