Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224918934> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4224918934 abstract "Audio-driven talking face, driving talking face by audio, has received considerable attention in multi-modal learning due to its widespread use in virtual reality. However, long-time recording of target high-quality video is needed by most existing audio-driven talking face studies, which significantly increases customization costs. This paper proposes a novel data-efficient audio-driven talking face generation method, which uses just a short target video to produce both lip-synchronized and high-definition face video driven by arbitrary audio in the wild. Current methods suffer from many problems, such as low definition, asynchronization of lip movement and voice, and intense demands for videos for training. In this work, the original target character’s face images are decomposed into 3D face model parameters including expression, geometry, illumination, etc. Then, low-definition pseudo video generated by an adapted target face video bridges the powerful pre-trained audio-driven model to our audio-to-expression transformation network and help to transfer the ability of audio-identity disentanglement. The expression is replaced via an audio and then combined with other face parameters to render a synthetic face. Finally, a neural rendering network translates the synthetic face into talking face without loss of definition. Experimental results show that the proposed method has the best performance in high-definition image quality, and comparable performance in lip synchronization compared with the existing state-of-the-art methods." @default.
- W4224918934 created "2022-04-28" @default.
- W4224918934 creator A5012753527 @default.
- W4224918934 creator A5024837226 @default.
- W4224918934 creator A5042551057 @default.
- W4224918934 creator A5057233187 @default.
- W4224918934 creator A5073845819 @default.
- W4224918934 creator A5074966540 @default.
- W4224918934 creator A5082709206 @default.
- W4224918934 creator A5088623594 @default.
- W4224918934 date "2022-05-23" @default.
- W4224918934 modified "2023-10-16" @default.
- W4224918934 title "Meta Talk: Learning To Data-Efficiently Generate Audio-Driven Lip-Synchronized Talking Face With High Definition" @default.
- W4224918934 cites W2017107803 @default.
- W4224918934 cites W2105649179 @default.
- W4224918934 cites W2107037917 @default.
- W4224918934 cites W2803705807 @default.
- W4224918934 cites W2944294033 @default.
- W4224918934 cites W2964449965 @default.
- W4224918934 cites W3081492798 @default.
- W4224918934 cites W3087121792 @default.
- W4224918934 cites W3202128205 @default.
- W4224918934 cites W3204680331 @default.
- W4224918934 doi "https://doi.org/10.1109/icassp43922.2022.9747284" @default.
- W4224918934 hasPublicationYear "2022" @default.
- W4224918934 type Work @default.
- W4224918934 citedByCount "2" @default.
- W4224918934 countsByYear W42249189342023 @default.
- W4224918934 crossrefType "proceedings-article" @default.
- W4224918934 hasAuthorship W4224918934A5012753527 @default.
- W4224918934 hasAuthorship W4224918934A5024837226 @default.
- W4224918934 hasAuthorship W4224918934A5042551057 @default.
- W4224918934 hasAuthorship W4224918934A5057233187 @default.
- W4224918934 hasAuthorship W4224918934A5073845819 @default.
- W4224918934 hasAuthorship W4224918934A5074966540 @default.
- W4224918934 hasAuthorship W4224918934A5082709206 @default.
- W4224918934 hasAuthorship W4224918934A5088623594 @default.
- W4224918934 hasConcept C127220857 @default.
- W4224918934 hasConcept C13895895 @default.
- W4224918934 hasConcept C144024400 @default.
- W4224918934 hasConcept C154945302 @default.
- W4224918934 hasConcept C160372630 @default.
- W4224918934 hasConcept C167310288 @default.
- W4224918934 hasConcept C199360897 @default.
- W4224918934 hasConcept C205711294 @default.
- W4224918934 hasConcept C2779304628 @default.
- W4224918934 hasConcept C28490314 @default.
- W4224918934 hasConcept C31972630 @default.
- W4224918934 hasConcept C36289849 @default.
- W4224918934 hasConcept C41008148 @default.
- W4224918934 hasConcept C49774154 @default.
- W4224918934 hasConcept C64922751 @default.
- W4224918934 hasConcept C90559484 @default.
- W4224918934 hasConceptScore W4224918934C127220857 @default.
- W4224918934 hasConceptScore W4224918934C13895895 @default.
- W4224918934 hasConceptScore W4224918934C144024400 @default.
- W4224918934 hasConceptScore W4224918934C154945302 @default.
- W4224918934 hasConceptScore W4224918934C160372630 @default.
- W4224918934 hasConceptScore W4224918934C167310288 @default.
- W4224918934 hasConceptScore W4224918934C199360897 @default.
- W4224918934 hasConceptScore W4224918934C205711294 @default.
- W4224918934 hasConceptScore W4224918934C2779304628 @default.
- W4224918934 hasConceptScore W4224918934C28490314 @default.
- W4224918934 hasConceptScore W4224918934C31972630 @default.
- W4224918934 hasConceptScore W4224918934C36289849 @default.
- W4224918934 hasConceptScore W4224918934C41008148 @default.
- W4224918934 hasConceptScore W4224918934C49774154 @default.
- W4224918934 hasConceptScore W4224918934C64922751 @default.
- W4224918934 hasConceptScore W4224918934C90559484 @default.
- W4224918934 hasLocation W42249189341 @default.
- W4224918934 hasOpenAccess W4224918934 @default.
- W4224918934 hasPrimaryLocation W42249189341 @default.
- W4224918934 hasRelatedWork W1863533157 @default.
- W4224918934 hasRelatedWork W2048402902 @default.
- W4224918934 hasRelatedWork W2098934641 @default.
- W4224918934 hasRelatedWork W2103413230 @default.
- W4224918934 hasRelatedWork W2143802570 @default.
- W4224918934 hasRelatedWork W2170815394 @default.
- W4224918934 hasRelatedWork W2792033502 @default.
- W4224918934 hasRelatedWork W3043119899 @default.
- W4224918934 hasRelatedWork W4234540277 @default.
- W4224918934 hasRelatedWork W4382560817 @default.
- W4224918934 isParatext "false" @default.
- W4224918934 isRetracted "false" @default.
- W4224918934 workType "article" @default.