Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382461570> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4382461570 endingPage "2208" @default.
- W4382461570 startingPage "2200" @default.
- W4382461570 abstract "Face reenactment and reconstruction benefit various applications in self-media, VR, etc. Recent face reenactment methods use 2D facial landmarks to implicitly retarget facial expressions and poses from driving videos to source images, while they suffer from pose and expression preservation issues for cross-identity scenarios, i.e., when the source and the driving subjects are different. Current self-supervised face reconstruction methods also demonstrate impressive results. However, these methods do not handle large expressions well, since their training data lacks samples of large expressions, and 2D facial attributes are inaccurate on such samples. To mitigate the above problems, we propose to explore the inner connection between the two tasks, i.e., using face reconstruction to provide sufficient 3D information for reenactment, and synthesizing videos paired with captured face model parameters through face reenactment to enhance the expression module of face reconstruction. In particular, we propose a novel cascade framework named JR2Net for Joint Face Reconstruction and Reenactment, which begins with the training of a coarse reconstruction network, followed by a 3D-aware face reenactment network based on the coarse reconstruction results. In the end, we train an expression tracking network based on our synthesized videos composed by image-face model parameter pairs. Such an expression tracking network can further enhance the coarse face reconstruction. Extensive experiments show that our JR2Net outperforms the state-of-the-art methods on several face reconstruction and reenactment benchmarks." @default.
- W4382461570 created "2023-06-29" @default.
- W4382461570 creator A5004716468 @default.
- W4382461570 creator A5008384374 @default.
- W4382461570 creator A5008560050 @default.
- W4382461570 creator A5022159272 @default.
- W4382461570 creator A5042888742 @default.
- W4382461570 creator A5059683257 @default.
- W4382461570 creator A5073451639 @default.
- W4382461570 creator A5075855277 @default.
- W4382461570 date "2023-06-26" @default.
- W4382461570 modified "2023-09-30" @default.
- W4382461570 title "JR2Net: Joint Monocular 3D Face Reconstruction and Reenactment" @default.
- W4382461570 doi "https://doi.org/10.1609/aaai.v37i2.25314" @default.
- W4382461570 hasPublicationYear "2023" @default.
- W4382461570 type Work @default.
- W4382461570 citedByCount "0" @default.
- W4382461570 crossrefType "journal-article" @default.
- W4382461570 hasAuthorship W4382461570A5004716468 @default.
- W4382461570 hasAuthorship W4382461570A5008384374 @default.
- W4382461570 hasAuthorship W4382461570A5008560050 @default.
- W4382461570 hasAuthorship W4382461570A5022159272 @default.
- W4382461570 hasAuthorship W4382461570A5042888742 @default.
- W4382461570 hasAuthorship W4382461570A5059683257 @default.
- W4382461570 hasAuthorship W4382461570A5073451639 @default.
- W4382461570 hasAuthorship W4382461570A5075855277 @default.
- W4382461570 hasBestOaLocation W43824615701 @default.
- W4382461570 hasConcept C109950114 @default.
- W4382461570 hasConcept C121332964 @default.
- W4382461570 hasConcept C144024400 @default.
- W4382461570 hasConcept C153180895 @default.
- W4382461570 hasConcept C154945302 @default.
- W4382461570 hasConcept C195704467 @default.
- W4382461570 hasConcept C199360897 @default.
- W4382461570 hasConcept C24890656 @default.
- W4382461570 hasConcept C2778355321 @default.
- W4382461570 hasConcept C2779304628 @default.
- W4382461570 hasConcept C31972630 @default.
- W4382461570 hasConcept C36289849 @default.
- W4382461570 hasConcept C41008148 @default.
- W4382461570 hasConcept C65909025 @default.
- W4382461570 hasConcept C90559484 @default.
- W4382461570 hasConceptScore W4382461570C109950114 @default.
- W4382461570 hasConceptScore W4382461570C121332964 @default.
- W4382461570 hasConceptScore W4382461570C144024400 @default.
- W4382461570 hasConceptScore W4382461570C153180895 @default.
- W4382461570 hasConceptScore W4382461570C154945302 @default.
- W4382461570 hasConceptScore W4382461570C195704467 @default.
- W4382461570 hasConceptScore W4382461570C199360897 @default.
- W4382461570 hasConceptScore W4382461570C24890656 @default.
- W4382461570 hasConceptScore W4382461570C2778355321 @default.
- W4382461570 hasConceptScore W4382461570C2779304628 @default.
- W4382461570 hasConceptScore W4382461570C31972630 @default.
- W4382461570 hasConceptScore W4382461570C36289849 @default.
- W4382461570 hasConceptScore W4382461570C41008148 @default.
- W4382461570 hasConceptScore W4382461570C65909025 @default.
- W4382461570 hasConceptScore W4382461570C90559484 @default.
- W4382461570 hasIssue "2" @default.
- W4382461570 hasLocation W43824615701 @default.
- W4382461570 hasOpenAccess W4382461570 @default.
- W4382461570 hasPrimaryLocation W43824615701 @default.
- W4382461570 hasRelatedWork W197633916 @default.
- W4382461570 hasRelatedWork W2040320435 @default.
- W4382461570 hasRelatedWork W2126637542 @default.
- W4382461570 hasRelatedWork W2138569648 @default.
- W4382461570 hasRelatedWork W2358483727 @default.
- W4382461570 hasRelatedWork W2980953096 @default.
- W4382461570 hasRelatedWork W3014239205 @default.
- W4382461570 hasRelatedWork W3121134787 @default.
- W4382461570 hasRelatedWork W3183290586 @default.
- W4382461570 hasRelatedWork W3192645019 @default.
- W4382461570 hasVolume "37" @default.
- W4382461570 isParatext "false" @default.
- W4382461570 isRetracted "false" @default.
- W4382461570 workType "article" @default.