Matches in SemOpenAlex for { <https://semopenalex.org/work/W2772024431> ?p ?o ?g. }
- W2772024431 abstract "Recently proposed robust 3D face alignment methods establish either dense or sparse correspondence between a 3D face model and a 2D facial image. The use of these methods presents new challenges as well as opportunities for facial texture analysis. In particular, by sampling the image using the fitted model, a facial UV can be created. Unfortunately, due to self-occlusion, such a UV map is always incomplete. In this paper, we propose a framework for training Deep Convolutional Neural Network (DCNN) to complete the facial UV map extracted from in-the-wild images. To this end, we first gather complete UV maps by fitting a 3D Morphable Model (3DMM) to various multiview image and video datasets, as well as leveraging on a new 3D dataset with over 3,000 identities. Second, we devise a meticulously designed architecture that combines local and global adversarial DCNNs to learn an identity-preserving facial UV completion model. We demonstrate that by attaching the completed UV to the fitted mesh and generating instances of arbitrary poses, we can increase pose variations for training deep face recognition/verification models, and minimise pose discrepancy during testing, which lead to better performance. Experiments on both controlled and in-the-wild UV datasets prove the effectiveness of our adversarial UV completion model. We achieve state-of-the-art verification accuracy, 94.05%, under the CFP frontal-profile protocol only by combining pose augmentation during training and pose discrepancy reduction during testing. We will release the first in-the-wild UV dataset (we refer as WildUV) that comprises of complete facial UV maps from 1,892 identities for research purposes." @default.
- W2772024431 created "2017-12-22" @default.
- W2772024431 creator A5017072420 @default.
- W2772024431 creator A5033539534 @default.
- W2772024431 creator A5073110676 @default.
- W2772024431 creator A5080553022 @default.
- W2772024431 creator A5088680073 @default.
- W2772024431 date "2018-06-01" @default.
- W2772024431 modified "2023-09-30" @default.
- W2772024431 title "UV-GAN: Adversarial Facial UV Map Completion for Pose-Invariant Face Recognition" @default.
- W2772024431 cites W2070604790 @default.
- W2772024431 cites W2133665775 @default.
- W2772024431 cites W2145287260 @default.
- W2772024431 cites W2194775991 @default.
- W2772024431 cites W2404498690 @default.
- W2772024431 cites W2431101926 @default.
- W2772024431 cites W2507920704 @default.
- W2772024431 cites W2557414982 @default.
- W2772024431 cites W2582523095 @default.
- W2772024431 cites W2611104282 @default.
- W2772024431 cites W2737047298 @default.
- W2772024431 cites W2737608545 @default.
- W2772024431 cites W2738588019 @default.
- W2772024431 cites W2769786287 @default.
- W2772024431 cites W2912990735 @default.
- W2772024431 cites W2963100452 @default.
- W2772024431 cites W2963420272 @default.
- W2772024431 cites W2963466847 @default.
- W2772024431 cites W2963896050 @default.
- W2772024431 cites W2964014798 @default.
- W2772024431 cites W2964337551 @default.
- W2772024431 cites W3099206234 @default.
- W2772024431 cites W3101036461 @default.
- W2772024431 cites W3101998545 @default.
- W2772024431 cites W3104792420 @default.
- W2772024431 doi "https://doi.org/10.1109/cvpr.2018.00741" @default.
- W2772024431 hasPublicationYear "2018" @default.
- W2772024431 type Work @default.
- W2772024431 sameAs 2772024431 @default.
- W2772024431 citedByCount "147" @default.
- W2772024431 countsByYear W27720244312018 @default.
- W2772024431 countsByYear W27720244312019 @default.
- W2772024431 countsByYear W27720244312020 @default.
- W2772024431 countsByYear W27720244312021 @default.
- W2772024431 countsByYear W27720244312022 @default.
- W2772024431 countsByYear W27720244312023 @default.
- W2772024431 crossrefType "proceedings-article" @default.
- W2772024431 hasAuthorship W2772024431A5017072420 @default.
- W2772024431 hasAuthorship W2772024431A5033539534 @default.
- W2772024431 hasAuthorship W2772024431A5073110676 @default.
- W2772024431 hasAuthorship W2772024431A5080553022 @default.
- W2772024431 hasAuthorship W2772024431A5088680073 @default.
- W2772024431 hasBestOaLocation W27720244312 @default.
- W2772024431 hasConcept C108583219 @default.
- W2772024431 hasConcept C115961682 @default.
- W2772024431 hasConcept C144024400 @default.
- W2772024431 hasConcept C153180895 @default.
- W2772024431 hasConcept C154945302 @default.
- W2772024431 hasConcept C190470478 @default.
- W2772024431 hasConcept C2779304628 @default.
- W2772024431 hasConcept C31510193 @default.
- W2772024431 hasConcept C31972630 @default.
- W2772024431 hasConcept C33923547 @default.
- W2772024431 hasConcept C36289849 @default.
- W2772024431 hasConcept C37736160 @default.
- W2772024431 hasConcept C37914503 @default.
- W2772024431 hasConcept C41008148 @default.
- W2772024431 hasConcept C81363708 @default.
- W2772024431 hasConceptScore W2772024431C108583219 @default.
- W2772024431 hasConceptScore W2772024431C115961682 @default.
- W2772024431 hasConceptScore W2772024431C144024400 @default.
- W2772024431 hasConceptScore W2772024431C153180895 @default.
- W2772024431 hasConceptScore W2772024431C154945302 @default.
- W2772024431 hasConceptScore W2772024431C190470478 @default.
- W2772024431 hasConceptScore W2772024431C2779304628 @default.
- W2772024431 hasConceptScore W2772024431C31510193 @default.
- W2772024431 hasConceptScore W2772024431C31972630 @default.
- W2772024431 hasConceptScore W2772024431C33923547 @default.
- W2772024431 hasConceptScore W2772024431C36289849 @default.
- W2772024431 hasConceptScore W2772024431C37736160 @default.
- W2772024431 hasConceptScore W2772024431C37914503 @default.
- W2772024431 hasConceptScore W2772024431C41008148 @default.
- W2772024431 hasConceptScore W2772024431C81363708 @default.
- W2772024431 hasLocation W27720244311 @default.
- W2772024431 hasLocation W27720244312 @default.
- W2772024431 hasLocation W27720244313 @default.
- W2772024431 hasOpenAccess W2772024431 @default.
- W2772024431 hasPrimaryLocation W27720244311 @default.
- W2772024431 hasRelatedWork W1775397219 @default.
- W2772024431 hasRelatedWork W2025991752 @default.
- W2772024431 hasRelatedWork W2347601237 @default.
- W2772024431 hasRelatedWork W2731899572 @default.
- W2772024431 hasRelatedWork W2897995864 @default.
- W2772024431 hasRelatedWork W2908959303 @default.
- W2772024431 hasRelatedWork W3000866861 @default.
- W2772024431 hasRelatedWork W3133861977 @default.
- W2772024431 hasRelatedWork W4312417841 @default.
- W2772024431 hasRelatedWork W4321369474 @default.
- W2772024431 isParatext "false" @default.
- W2772024431 isRetracted "false" @default.