FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328029534> ?p ?o ?g. }

• W4328029534 endingPage "622" @default.
• W4328029534 startingPage "611" @default.
• W4328029534 abstract "Abstract Face swapping is the process of applying a source actor's appearance to a target actor's performance in a video. This is a challenging visual effect that has seen increasing demand in film and television production. Recent work has shown that data‐driven methods based on deep learning can produce compelling effects at production quality in a fraction of the time required for a traditional 3D pipeline. However, the dominant approach operates only on 2D imagery without reference to the underlying facial geometry or texture, resulting in poor generalization under novel viewpoints and little artistic control. Methods that do incorporate geometry rely on pre‐learned facial priors that do not adapt well to particular geometric features of the source and target faces. We approach the problem of face swapping from the perspective of learning simultaneous convolutional facial autoencoders for the source and target identities, using a shared encoder network with identity‐specific decoders. The key novelty in our approach is that each decoder first lifts the latent code into a 3D representation, comprising a dynamic face texture and a deformable 3D face shape, before projecting this 3D face back onto the input image using a differentiable renderer. The coupled autoencoders are trained only on videos of the source and target identities, without requiring 3D supervision. By leveraging the learned 3D geometry and texture, our method achieves face swapping with higher quality than when using off‐the‐shelf monocular 3D face reconstruction, and overall lower FID score than state‐of‐the‐art 2D methods. Furthermore, our 3D representation allows for efficient artistic control over the result, which can be hard to achieve with existing 2D approaches." @default.
• W4328029534 created "2023-03-22" @default.
• W4328029534 creator A5011929840 @default.
• W4328029534 creator A5013194672 @default.
• W4328029534 creator A5018563642 @default.
• W4328029534 creator A5027873151 @default.
• W4328029534 creator A5033076979 @default.
• W4328029534 creator A5036716763 @default.
• W4328029534 creator A5050994184 @default.
• W4328029534 creator A5052388616 @default.
• W4328029534 creator A5057479316 @default.
• W4328029534 creator A5083414352 @default.
• W4328029534 creator A5084208625 @default.
• W4328029534 creator A5085618571 @default.
• W4328029534 date "2022-10-01" @default.
• W4328029534 modified "2023-10-02" @default.
• W4328029534 title "Learning Dynamic 3D Geometry and Texture for Video Face Swapping" @default.
• W4328029534 cites W1580389772 @default.
• W4328029534 cites W2107037917 @default.
• W4328029534 cites W2153709524 @default.
• W4328029534 cites W2160126058 @default.
• W4328029534 cites W2166465411 @default.
• W4328029534 cites W2237250383 @default.
• W4328029534 cites W2301937176 @default.
• W4328029534 cites W2341600683 @default.
• W4328029534 cites W2608058963 @default.
• W4328029534 cites W2806833697 @default.
• W4328029534 cites W2886934227 @default.
• W4328029534 cites W2902266071 @default.
• W4328029534 cites W2902812770 @default.
• W4328029534 cites W2902836694 @default.
• W4328029534 cites W2962778872 @default.
• W4328029534 cites W2962819150 @default.
• W4328029534 cites W2963342110 @default.
• W4328029534 cites W2964449965 @default.
• W4328029534 cites W2984700035 @default.
• W4328029534 cites W2989851933 @default.
• W4328029534 cites W3035574324 @default.
• W4328029534 cites W3038930935 @default.
• W4328029534 cites W3043844802 @default.
• W4328029534 cites W3101531717 @default.
• W4328029534 cites W3104300620 @default.
• W4328029534 cites W3174171554 @default.
• W4328029534 cites W4224991903 @default.
• W4328029534 cites W4236231454 @default.
• W4328029534 cites W4312551140 @default.
• W4328029534 cites W4313068475 @default.
• W4328029534 doi "https://doi.org/10.1111/cgf.14705" @default.
• W4328029534 hasPublicationYear "2022" @default.
• W4328029534 type Work @default.
• W4328029534 citedByCount "0" @default.
• W4328029534 crossrefType "journal-article" @default.
• W4328029534 hasAuthorship W4328029534A5011929840 @default.
• W4328029534 hasAuthorship W4328029534A5013194672 @default.
• W4328029534 hasAuthorship W4328029534A5018563642 @default.
• W4328029534 hasAuthorship W4328029534A5027873151 @default.
• W4328029534 hasAuthorship W4328029534A5033076979 @default.
• W4328029534 hasAuthorship W4328029534A5036716763 @default.
• W4328029534 hasAuthorship W4328029534A5050994184 @default.
• W4328029534 hasAuthorship W4328029534A5052388616 @default.
• W4328029534 hasAuthorship W4328029534A5057479316 @default.
• W4328029534 hasAuthorship W4328029534A5083414352 @default.
• W4328029534 hasAuthorship W4328029534A5084208625 @default.
• W4328029534 hasAuthorship W4328029534A5085618571 @default.
• W4328029534 hasConcept C101738243 @default.
• W4328029534 hasConcept C108583219 @default.
• W4328029534 hasConcept C111919701 @default.
• W4328029534 hasConcept C118505674 @default.
• W4328029534 hasConcept C144024400 @default.
• W4328029534 hasConcept C153180895 @default.
• W4328029534 hasConcept C154945302 @default.
• W4328029534 hasConcept C205711294 @default.
• W4328029534 hasConcept C2776449333 @default.
• W4328029534 hasConcept C2779304628 @default.
• W4328029534 hasConcept C31972630 @default.
• W4328029534 hasConcept C36289849 @default.
• W4328029534 hasConcept C41008148 @default.
• W4328029534 hasConcept C50637493 @default.
• W4328029534 hasConcept C65909025 @default.
• W4328029534 hasConcept C81363708 @default.
• W4328029534 hasConceptScore W4328029534C101738243 @default.
• W4328029534 hasConceptScore W4328029534C108583219 @default.
• W4328029534 hasConceptScore W4328029534C111919701 @default.
• W4328029534 hasConceptScore W4328029534C118505674 @default.
• W4328029534 hasConceptScore W4328029534C144024400 @default.
• W4328029534 hasConceptScore W4328029534C153180895 @default.
• W4328029534 hasConceptScore W4328029534C154945302 @default.
• W4328029534 hasConceptScore W4328029534C205711294 @default.
• W4328029534 hasConceptScore W4328029534C2776449333 @default.
• W4328029534 hasConceptScore W4328029534C2779304628 @default.
• W4328029534 hasConceptScore W4328029534C31972630 @default.
• W4328029534 hasConceptScore W4328029534C36289849 @default.
• W4328029534 hasConceptScore W4328029534C41008148 @default.
• W4328029534 hasConceptScore W4328029534C50637493 @default.
• W4328029534 hasConceptScore W4328029534C65909025 @default.
• W4328029534 hasConceptScore W4328029534C81363708 @default.
• W4328029534 hasIssue "7" @default.
• W4328029534 hasLocation W43280295341 @default.

• next