FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3099505600> ?p ?o ?g. }

• W3099505600 endingPage "1172" @default.
• W3099505600 startingPage "1160" @default.
• W3099505600 abstract "3D face reconstruction from a single 2D image is a challenging problem with broad applications. Recent methods typically aim to learn a CNN-based 3D face model that regresses coefficients of 3D Morphable Model (3DMM) from 2D images to render 3D face reconstruction or dense face alignment. However, the shortage of training data with 3D annotations considerably limits performance of those methods. To alleviate this issue, we propose a novel 2D-assisted self-supervised learning (2DASL) method that can effectively use in-the-wild 2D face images with noisy landmark information to substantially improve 3D face model learning. Specifically, taking the sparse 2D facial landmarks as additional information, 2DSAL introduces four novel self-supervision schemes that view the 2D landmark and 3D landmark prediction as a self-mapping process, including the 2D and 3D landmark self-prediction consistency, cycle-consistency over the 2D landmark prediction and self-critic over the predicted 3DMM coefficients based on landmark predictions. Using these four self-supervision schemes, the 2DASL method significantly relieves demands on the the conventional paired 2D-to-3D annotations and gives much higher-quality 3D face models without requiring any additional 3D annotations. Experiments on multiple challenging datasets show that our method outperforms state-of-the-arts for both 3D face reconstruction and dense face alignment by a large margin." @default.
• W3099505600 created "2020-11-23" @default.
• W3099505600 creator A5013979705 @default.
• W3099505600 creator A5028268055 @default.
• W3099505600 creator A5029972506 @default.
• W3099505600 creator A5033884558 @default.
• W3099505600 creator A5050342541 @default.
• W3099505600 creator A5072421286 @default.
• W3099505600 creator A5075445800 @default.
• W3099505600 creator A5078587654 @default.
• W3099505600 creator A5086595168 @default.
• W3099505600 creator A5087384752 @default.
• W3099505600 date "2021-01-01" @default.
• W3099505600 modified "2023-10-14" @default.
• W3099505600 title "3D Face Reconstruction From A Single Image Assisted by 2D Face Images in the Wild" @default.
• W3099505600 cites W1567532702 @default.
• W3099505600 cites W1682276745 @default.
• W3099505600 cites W1834627138 @default.
• W3099505600 cites W1946919140 @default.
• W3099505600 cites W1977821862 @default.
• W3099505600 cites W2012885984 @default.
• W3099505600 cites W2017107803 @default.
• W3099505600 cites W2036868818 @default.
• W3099505600 cites W2055603434 @default.
• W3099505600 cites W2058961190 @default.
• W3099505600 cites W2076017598 @default.
• W3099505600 cites W2086331119 @default.
• W3099505600 cites W2087007396 @default.
• W3099505600 cites W2101812986 @default.
• W3099505600 cites W2101866605 @default.
• W3099505600 cites W2107037917 @default.
• W3099505600 cites W2126552487 @default.
• W3099505600 cites W2136000821 @default.
• W3099505600 cites W2136863438 @default.
• W3099505600 cites W2138829353 @default.
• W3099505600 cites W2146566773 @default.
• W3099505600 cites W2152826865 @default.
• W3099505600 cites W2155211928 @default.
• W3099505600 cites W2156503193 @default.
• W3099505600 cites W2160126058 @default.
• W3099505600 cites W2165421528 @default.
• W3099505600 cites W2168722300 @default.
• W3099505600 cites W2194775991 @default.
• W3099505600 cites W2237250383 @default.
• W3099505600 cites W2300234500 @default.
• W3099505600 cites W2301789900 @default.
• W3099505600 cites W2364466243 @default.
• W3099505600 cites W2465108587 @default.
• W3099505600 cites W2471370490 @default.
• W3099505600 cites W2486034530 @default.
• W3099505600 cites W2487852963 @default.
• W3099505600 cites W2519131448 @default.
• W3099505600 cites W2520331172 @default.
• W3099505600 cites W2546505780 @default.
• W3099505600 cites W2546584497 @default.
• W3099505600 cites W2547163414 @default.
• W3099505600 cites W2548062649 @default.
• W3099505600 cites W2548615485 @default.
• W3099505600 cites W2548882894 @default.
• W3099505600 cites W2555510177 @default.
• W3099505600 cites W2584229793 @default.
• W3099505600 cites W2599226450 @default.
• W3099505600 cites W2605701576 @default.
• W3099505600 cites W2606794139 @default.
• W3099505600 cites W2737047298 @default.
• W3099505600 cites W2748448865 @default.
• W3099505600 cites W2796822548 @default.
• W3099505600 cites W2798807671 @default.
• W3099505600 cites W2808174311 @default.
• W3099505600 cites W2883861033 @default.
• W3099505600 cites W2884066303 @default.
• W3099505600 cites W2942765547 @default.
• W3099505600 cites W2963073614 @default.
• W3099505600 cites W2963202462 @default.
• W3099505600 cites W2963253045 @default.
• W3099505600 cites W2963278718 @default.
• W3099505600 cites W2963342110 @default.
• W3099505600 cites W2963480351 @default.
• W3099505600 cites W2963544488 @default.
• W3099505600 cites W2964014798 @default.
• W3099505600 cites W2964722723 @default.
• W3099505600 cites W2968614444 @default.
• W3099505600 cites W2987413615 @default.
• W3099505600 cites W3104792420 @default.
• W3099505600 cites W3106024060 @default.
• W3099505600 doi "https://doi.org/10.1109/tmm.2020.2993962" @default.
• W3099505600 hasPublicationYear "2021" @default.
• W3099505600 type Work @default.
• W3099505600 sameAs 3099505600 @default.
• W3099505600 citedByCount "49" @default.
• W3099505600 countsByYear W30995056002020 @default.
• W3099505600 countsByYear W30995056002021 @default.
• W3099505600 countsByYear W30995056002022 @default.
• W3099505600 countsByYear W30995056002023 @default.
• W3099505600 crossrefType "journal-article" @default.
• W3099505600 hasAuthorship W3099505600A5013979705 @default.
• W3099505600 hasAuthorship W3099505600A5028268055 @default.
• W3099505600 hasAuthorship W3099505600A5029972506 @default.

• next