FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311805938> ?p ?o ?g. }

• W4311805938 endingPage "16" @default.
• W4311805938 startingPage "1" @default.
• W4311805938 abstract "Production-level workflows for producing convincing 3D dynamic human faces have long relied on an assortment of labor-intensive tools for geometry and texture generation, motion capture and rigging, and expression synthesis. Recent neural approaches automate individual components but the corresponding latent representations cannot provide artists with explicit controls as in conventional tools. In this paper, we present a new learning-based, video-driven approach for generating dynamic facial geometries with high-quality physically-based assets. For data collection, we construct a hybrid multiview-photometric capture stage, coupling with ultra-fast video cameras to obtain raw 3D facial assets. We then set out to model the facial expression, geometry and physically-based textures using separate VAEs where we impose a global MLP based expression mapping across the latent spaces of respective networks, to preserve characteristics across respective attributes. We also model the delta information as wrinkle maps for the physically-based textures, achieving high-quality 4K dynamic textures. We demonstrate our approach in high-fidelity performer-specific facial capture and cross-identity facial motion retargeting. In addition, our multi-VAE-based neural asset, along with the fast adaptation schemes, can also be deployed to handle in-the-wild videos. Besides, we motivate the utility of our explicit facial disentangling strategy by providing various promising physically-based editing results with high realism. Comprehensive experiments show that our technique provides higher accuracy and visual fidelity than previous video-driven facial reconstruction and animation methods." @default.
• W4311805938 created "2022-12-28" @default.
• W4311805938 creator A5016013285 @default.
• W4311805938 creator A5023657484 @default.
• W4311805938 creator A5038142929 @default.
• W4311805938 creator A5045222641 @default.
• W4311805938 creator A5053722464 @default.
• W4311805938 creator A5056815013 @default.
• W4311805938 creator A5087486639 @default.
• W4311805938 creator A5087775076 @default.
• W4311805938 date "2022-11-30" @default.
• W4311805938 modified "2023-10-15" @default.
• W4311805938 title "Video-Driven Neural Physically-Based Facial Asset for Production" @default.
• W4311805938 cites W1890563702 @default.
• W4311805938 cites W1896424170 @default.
• W4311805938 cites W1967554269 @default.
• W4311805938 cites W1984389259 @default.
• W4311805938 cites W2017107803 @default.
• W4311805938 cites W2038891881 @default.
• W4311805938 cites W2051297709 @default.
• W4311805938 cites W2062712751 @default.
• W4311805938 cites W2107037917 @default.
• W4311805938 cites W2115252128 @default.
• W4311805938 cites W2163131540 @default.
• W4311805938 cites W2235136907 @default.
• W4311805938 cites W2237250383 @default.
• W4311805938 cites W2542323081 @default.
• W4311805938 cites W2556634673 @default.
• W4311805938 cites W2560535660 @default.
• W4311805938 cites W2584229793 @default.
• W4311805938 cites W2623464795 @default.
• W4311805938 cites W2769666294 @default.
• W4311805938 cites W2798409702 @default.
• W4311805938 cites W2799185473 @default.
• W4311805938 cites W2803705807 @default.
• W4311805938 cites W2810993953 @default.
• W4311805938 cites W2811426698 @default.
• W4311805938 cites W2886974627 @default.
• W4311805938 cites W2903420996 @default.
• W4311805938 cites W2948127555 @default.
• W4311805938 cites W2957926190 @default.
• W4311805938 cites W2963342110 @default.
• W4311805938 cites W2963890275 @default.
• W4311805938 cites W2984700035 @default.
• W4311805938 cites W3000731301 @default.
• W4311805938 cites W3015873132 @default.
• W4311805938 cites W3034192160 @default.
• W4311805938 cites W3034771054 @default.
• W4311805938 cites W3034798648 @default.
• W4311805938 cites W3035201761 @default.
• W4311805938 cites W3048884441 @default.
• W4311805938 cites W3101531717 @default.
• W4311805938 cites W3104300620 @default.
• W4311805938 cites W3109154889 @default.
• W4311805938 cites W3109585842 @default.
• W4311805938 cites W3125747099 @default.
• W4311805938 cites W3126481101 @default.
• W4311805938 cites W3134122898 @default.
• W4311805938 cites W3152675032 @default.
• W4311805938 cites W3172500391 @default.
• W4311805938 cites W3175695459 @default.
• W4311805938 cites W3176503495 @default.
• W4311805938 cites W3178698064 @default.
• W4311805938 cites W3180589757 @default.
• W4311805938 cites W3180794345 @default.
• W4311805938 cites W3182714435 @default.
• W4311805938 cites W3183587701 @default.
• W4311805938 cites W3184291866 @default.
• W4311805938 cites W3201676401 @default.
• W4311805938 cites W3213788316 @default.
• W4311805938 cites W4200151550 @default.
• W4311805938 cites W4231149888 @default.
• W4311805938 cites W4288242633 @default.
• W4311805938 cites W4361851623 @default.
• W4311805938 cites W3202077208 @default.
• W4311805938 doi "https://doi.org/10.1145/3550454.3555445" @default.
• W4311805938 hasPublicationYear "2022" @default.
• W4311805938 type Work @default.
• W4311805938 citedByCount "2" @default.
• W4311805938 countsByYear W43118059382023 @default.
• W4311805938 crossrefType "journal-article" @default.
• W4311805938 hasAuthorship W4311805938A5016013285 @default.
• W4311805938 hasAuthorship W4311805938A5023657484 @default.
• W4311805938 hasAuthorship W4311805938A5038142929 @default.
• W4311805938 hasAuthorship W4311805938A5045222641 @default.
• W4311805938 hasAuthorship W4311805938A5053722464 @default.
• W4311805938 hasAuthorship W4311805938A5056815013 @default.
• W4311805938 hasAuthorship W4311805938A5087486639 @default.
• W4311805938 hasAuthorship W4311805938A5087775076 @default.
• W4311805938 hasBestOaLocation W43118059381 @default.
• W4311805938 hasConcept C104114177 @default.
• W4311805938 hasConcept C121684516 @default.
• W4311805938 hasConcept C138591656 @default.
• W4311805938 hasConcept C153180895 @default.
• W4311805938 hasConcept C154945302 @default.
• W4311805938 hasConcept C177212765 @default.
• W4311805938 hasConcept C195704467 @default.
• W4311805938 hasConcept C2778090530 @default.

• next