Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288776710> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4288776710 endingPage "16" @default.
- W4288776710 startingPage "7" @default.
- W4288776710 abstract "Monocular face reconstruction is a significant task in many multimedia applications. However, learning-based methods unequivocally suffer from the lack of large datasets annotated with 3-D ground truth. To tackle this problem, we proposed a novel end-to-end 3-D face reconstruction network consisting of a domain-transfer conditional GAN (cGAN) and a face reconstruction network. Our method first uses cGAN to translate the realistic face images to the specific rendered style, with a novel 2-D facial edge consistency loss function to exploit in-the-wild images. The domain-transferred images are then fed into a 3-D face reconstruction network. We further propose a novel reprojection consistency loss to restrict the 3-D face reconstruction network in a self-supervised way. Our approach can be trained with the annotated dataset, synthetic dataset, and in-the-wild images to learn a unified face model. Extensive experiments have demonstrated the effectiveness of our method." @default.
- W4288776710 created "2022-07-30" @default.
- W4288776710 creator A5010961909 @default.
- W4288776710 creator A5016150064 @default.
- W4288776710 creator A5018127347 @default.
- W4288776710 creator A5034342999 @default.
- W4288776710 creator A5050569926 @default.
- W4288776710 date "2023-01-01" @default.
- W4288776710 modified "2023-10-14" @default.
- W4288776710 title "Learning 3-D Face Shape From Diverse Sources With Cross-Domain Face Synthesis" @default.
- W4288776710 cites W2012885984 @default.
- W4288776710 cites W2086331119 @default.
- W4288776710 cites W2138829353 @default.
- W4288776710 cites W2237250383 @default.
- W4288776710 cites W2265959009 @default.
- W4288776710 cites W2519131448 @default.
- W4288776710 cites W2599226450 @default.
- W4288776710 cites W2962793481 @default.
- W4288776710 cites W2963073614 @default.
- W4288776710 cites W2963342110 @default.
- W4288776710 cites W2964449965 @default.
- W4288776710 cites W2988472682 @default.
- W4288776710 cites W3034512702 @default.
- W4288776710 cites W3093480222 @default.
- W4288776710 cites W3099505600 @default.
- W4288776710 cites W3104300620 @default.
- W4288776710 cites W3180794345 @default.
- W4288776710 doi "https://doi.org/10.1109/mmul.2022.3195091" @default.
- W4288776710 hasPublicationYear "2023" @default.
- W4288776710 type Work @default.
- W4288776710 citedByCount "0" @default.
- W4288776710 crossrefType "journal-article" @default.
- W4288776710 hasAuthorship W4288776710A5010961909 @default.
- W4288776710 hasAuthorship W4288776710A5016150064 @default.
- W4288776710 hasAuthorship W4288776710A5018127347 @default.
- W4288776710 hasAuthorship W4288776710A5034342999 @default.
- W4288776710 hasAuthorship W4288776710A5050569926 @default.
- W4288776710 hasConcept C108583219 @default.
- W4288776710 hasConcept C134306372 @default.
- W4288776710 hasConcept C144024400 @default.
- W4288776710 hasConcept C146849305 @default.
- W4288776710 hasConcept C153180895 @default.
- W4288776710 hasConcept C154945302 @default.
- W4288776710 hasConcept C2776436953 @default.
- W4288776710 hasConcept C2779304628 @default.
- W4288776710 hasConcept C31510193 @default.
- W4288776710 hasConcept C31972630 @default.
- W4288776710 hasConcept C33923547 @default.
- W4288776710 hasConcept C36289849 @default.
- W4288776710 hasConcept C36503486 @default.
- W4288776710 hasConcept C41008148 @default.
- W4288776710 hasConcept C65909025 @default.
- W4288776710 hasConceptScore W4288776710C108583219 @default.
- W4288776710 hasConceptScore W4288776710C134306372 @default.
- W4288776710 hasConceptScore W4288776710C144024400 @default.
- W4288776710 hasConceptScore W4288776710C146849305 @default.
- W4288776710 hasConceptScore W4288776710C153180895 @default.
- W4288776710 hasConceptScore W4288776710C154945302 @default.
- W4288776710 hasConceptScore W4288776710C2776436953 @default.
- W4288776710 hasConceptScore W4288776710C2779304628 @default.
- W4288776710 hasConceptScore W4288776710C31510193 @default.
- W4288776710 hasConceptScore W4288776710C31972630 @default.
- W4288776710 hasConceptScore W4288776710C33923547 @default.
- W4288776710 hasConceptScore W4288776710C36289849 @default.
- W4288776710 hasConceptScore W4288776710C36503486 @default.
- W4288776710 hasConceptScore W4288776710C41008148 @default.
- W4288776710 hasConceptScore W4288776710C65909025 @default.
- W4288776710 hasFunder F4320321001 @default.
- W4288776710 hasIssue "1" @default.
- W4288776710 hasLocation W42887767101 @default.
- W4288776710 hasOpenAccess W4288776710 @default.
- W4288776710 hasPrimaryLocation W42887767101 @default.
- W4288776710 hasRelatedWork W1560697087 @default.
- W4288776710 hasRelatedWork W1989039360 @default.
- W4288776710 hasRelatedWork W2023043839 @default.
- W4288776710 hasRelatedWork W2060029454 @default.
- W4288776710 hasRelatedWork W2136485282 @default.
- W4288776710 hasRelatedWork W2138569648 @default.
- W4288776710 hasRelatedWork W2146295394 @default.
- W4288776710 hasRelatedWork W2366097813 @default.
- W4288776710 hasRelatedWork W2378609488 @default.
- W4288776710 hasRelatedWork W2908959303 @default.
- W4288776710 hasVolume "30" @default.
- W4288776710 isParatext "false" @default.
- W4288776710 isRetracted "false" @default.
- W4288776710 workType "article" @default.