FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964449965> ?p ?o ?g. }

• W2964449965 abstract "Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency. However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce. In this paper, we propose a novel deep 3D face reconstruction approach that 1) leverages a robust, hybrid loss function for weakly-supervised learning which takes into account both low-level and perception-level information for supervision, and 2) performs multi-image face reconstruction by exploiting complementary information from different images for shape aggregation. Our method is fast, accurate, and robust to occlusion and large pose. We provide comprehensive experiments on MICC Florence and Facewarehouse datasets, systematically comparing our method with fifteen recent methods and demonstrating its state-of-the-art performance. Code available at https://github.com/Microsoft/Deep3DFaceReconstruction" @default.
• W2964449965 created "2019-08-13" @default.
• W2964449965 creator A5007759097 @default.
• W2964449965 creator A5045624501 @default.
• W2964449965 creator A5064291165 @default.
• W2964449965 creator A5076804411 @default.
• W2964449965 creator A5077900121 @default.
• W2964449965 creator A5090954747 @default.
• W2964449965 date "2019-06-01" @default.
• W2964449965 modified "2023-10-18" @default.
• W2964449965 title "Accurate 3D Face Reconstruction With Weakly-Supervised Learning: From Single Image to Image Set" @default.
• W2964449965 cites W125358319 @default.
• W2964449965 cites W1498150497 @default.
• W2964449965 cites W1834627138 @default.
• W2964449965 cites W1916406603 @default.
• W2964449965 cites W1940113235 @default.
• W2964449965 cites W1949778830 @default.
• W2964449965 cites W2017107803 @default.
• W2964449965 cites W2038891881 @default.
• W2964449965 cites W2086331119 @default.
• W2964449965 cites W2087007396 @default.
• W2964449965 cites W2099478163 @default.
• W2964449965 cites W2105649179 @default.
• W2964449965 cites W2107037917 @default.
• W2964449965 cites W2116264069 @default.
• W2964449965 cites W2117539524 @default.
• W2964449965 cites W2134724684 @default.
• W2964449965 cites W2135666716 @default.
• W2964449965 cites W2136863438 @default.
• W2964449965 cites W2153746365 @default.
• W2964449965 cites W2155211928 @default.
• W2964449965 cites W2160126058 @default.
• W2964449965 cites W2194775991 @default.
• W2964449965 cites W2237250383 @default.
• W2964449965 cites W2261888986 @default.
• W2964449965 cites W2339268922 @default.
• W2964449965 cites W2398381847 @default.
• W2964449965 cites W2431101926 @default.
• W2964449965 cites W2464650832 @default.
• W2964449965 cites W2467255717 @default.
• W2964449965 cites W2486034530 @default.
• W2964449965 cites W2495387757 @default.
• W2964449965 cites W2519131448 @default.
• W2964449965 cites W2555510177 @default.
• W2964449965 cites W2584229793 @default.
• W2964449965 cites W2599226450 @default.
• W2964449965 cites W2605701576 @default.
• W2964449965 cites W2748448865 @default.
• W2964449965 cites W2769375465 @default.
• W2964449965 cites W2771328060 @default.
• W2964449965 cites W2795709097 @default.
• W2964449965 cites W2796822548 @default.
• W2964449965 cites W2798291180 @default.
• W2964449965 cites W2798896170 @default.
• W2964449965 cites W2803705807 @default.
• W2964449965 cites W2912990735 @default.
• W2964449965 cites W2962780596 @default.
• W2964449965 cites W2963559058 @default.
• W2964449965 cites W2963915677 @default.
• W2964449965 cites W2964014798 @default.
• W2964449965 cites W2964094607 @default.
• W2964449965 cites W3099206234 @default.
• W2964449965 cites W3104792420 @default.
• W2964449965 doi "https://doi.org/10.1109/cvprw.2019.00038" @default.
• W2964449965 hasPublicationYear "2019" @default.
• W2964449965 type Work @default.
• W2964449965 sameAs 2964449965 @default.
• W2964449965 citedByCount "311" @default.
• W2964449965 countsByYear W29644499652018 @default.
• W2964449965 countsByYear W29644499652020 @default.
• W2964449965 countsByYear W29644499652021 @default.
• W2964449965 countsByYear W29644499652022 @default.
• W2964449965 countsByYear W29644499652023 @default.
• W2964449965 crossrefType "proceedings-article" @default.
• W2964449965 hasAuthorship W2964449965A5007759097 @default.
• W2964449965 hasAuthorship W2964449965A5045624501 @default.
• W2964449965 hasAuthorship W2964449965A5064291165 @default.
• W2964449965 hasAuthorship W2964449965A5076804411 @default.
• W2964449965 hasAuthorship W2964449965A5077900121 @default.
• W2964449965 hasAuthorship W2964449965A5090954747 @default.
• W2964449965 hasBestOaLocation W29644499652 @default.
• W2964449965 hasConcept C108583219 @default.
• W2964449965 hasConcept C115961682 @default.
• W2964449965 hasConcept C141379421 @default.
• W2964449965 hasConcept C144024400 @default.
• W2964449965 hasConcept C146849305 @default.
• W2964449965 hasConcept C153180895 @default.
• W2964449965 hasConcept C154945302 @default.
• W2964449965 hasConcept C177264268 @default.
• W2964449965 hasConcept C199360897 @default.
• W2964449965 hasConcept C2776760102 @default.
• W2964449965 hasConcept C2779304628 @default.
• W2964449965 hasConcept C31510193 @default.
• W2964449965 hasConcept C31972630 @default.
• W2964449965 hasConcept C36289849 @default.
• W2964449965 hasConcept C41008148 @default.
• W2964449965 hasConceptScore W2964449965C108583219 @default.
• W2964449965 hasConceptScore W2964449965C115961682 @default.
• W2964449965 hasConceptScore W2964449965C141379421 @default.
• W2964449965 hasConceptScore W2964449965C144024400 @default.

• next