FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204133863> ?p ?o ?g. }

• W3204133863 abstract "High-fidelity face digitization solutions often combine multi-view stereo (MVS) techniques for 3D reconstruction and a non-rigid registration step to establish dense correspondence across identities and expressions. A common problem is the need for manual clean-up after the MVS step, as 3D scans are typically affected by noise and outliers and contain hairy surface regions that need to be cleaned up by artists. Furthermore, mesh registration tends to fail for extreme facial expressions. Most learning-based methods use an underlying 3D morphable model (3DMM) to ensure robustness, but this limits the output accuracy for extreme facial expressions. In addition, the global bottleneck of regression architectures cannot produce meshes that tightly fit the ground truth surfaces. We propose ToFu, Topologically consistent Face from multi-view, a geometry inference framework that can produce topologically consistent meshes across facial identities and expressions using a volumetric representation instead of an explicit underlying 3DMM. Our novel progressive mesh generation network embeds the topological structure of the face in a feature volume, sampled from geometry-aware local features. A coarse-to-fine architecture facilitates dense and accurate facial mesh predictions in a consistent mesh topology. ToFu further captures displacement maps for pore-level geometric details and facilitates high-quality rendering in the form of albedo and specular reflectance maps. These high-quality assets are readily usable by production studios for avatar creation, animation and physically-based skin rendering. We demonstrate state-of-the-art geometric and correspondence accuracy, while only taking 0.385 seconds to compute a mesh with 10K vertices, which is three orders of magnitude faster than traditional techniques. The code and the model are available for research purposes at https://tianyeli.github.io/tofu." @default.
• W3204133863 created "2021-10-11" @default.
• W3204133863 creator A5003720426 @default.
• W3204133863 creator A5005369320 @default.
• W3204133863 creator A5006442099 @default.
• W3204133863 creator A5025958423 @default.
• W3204133863 creator A5032894412 @default.
• W3204133863 creator A5079732143 @default.
• W3204133863 date "2021-10-06" @default.
• W3204133863 modified "2023-09-23" @default.
• W3204133863 title "Topologically Consistent Multi-View Face Inference Using Volumetric Sampling" @default.
• W3204133863 cites W1638031671 @default.
• W3204133863 cites W1781337833 @default.
• W3204133863 cites W1901129140 @default.
• W3204133863 cites W1985290145 @default.
• W3204133863 cites W1986049249 @default.
• W3204133863 cites W2013871799 @default.
• W3204133863 cites W2048359624 @default.
• W3204133863 cites W2069997605 @default.
• W3204133863 cites W2100810849 @default.
• W3204133863 cites W2102924784 @default.
• W3204133863 cites W2107813907 @default.
• W3204133863 cites W2120420721 @default.
• W3204133863 cites W2132055825 @default.
• W3204133863 cites W2148457221 @default.
• W3204133863 cites W2158778494 @default.
• W3204133863 cites W2167085613 @default.
• W3204133863 cites W2167141871 @default.
• W3204133863 cites W2180648442 @default.
• W3204133863 cites W2194775991 @default.
• W3204133863 cites W2235136907 @default.
• W3204133863 cites W2237250383 @default.
• W3204133863 cites W2261888986 @default.
• W3204133863 cites W2301937176 @default.
• W3204133863 cites W2461748234 @default.
• W3204133863 cites W2519131448 @default.
• W3204133863 cites W2604672468 @default.
• W3204133863 cites W2608696995 @default.
• W3204133863 cites W2746892480 @default.
• W3204133863 cites W2769375465 @default.
• W3204133863 cites W2769666294 @default.
• W3204133863 cites W2771328060 @default.
• W3204133863 cites W2795709097 @default.
• W3204133863 cites W2798291180 @default.
• W3204133863 cites W2883221003 @default.
• W3204133863 cites W2891158090 @default.
• W3204133863 cites W2896628364 @default.
• W3204133863 cites W2902836694 @default.
• W3204133863 cites W2903420996 @default.
• W3204133863 cites W2909918887 @default.
• W3204133863 cites W2945729334 @default.
• W3204133863 cites W2962793285 @default.
• W3204133863 cites W2962860871 @default.
• W3204133863 cites W2963451207 @default.
• W3204133863 cites W2963800363 @default.
• W3204133863 cites W2963966978 @default.
• W3204133863 cites W2964176417 @default.
• W3204133863 cites W2968257580 @default.
• W3204133863 cites W2970131683 @default.
• W3204133863 cites W2979574537 @default.
• W3204133863 cites W3009246422 @default.
• W3204133863 cites W3015873132 @default.
• W3204133863 cites W3034192160 @default.
• W3204133863 cites W3034530552 @default.
• W3204133863 cites W3035174858 @default.
• W3204133863 cites W3048884441 @default.
• W3204133863 cites W3100398946 @default.
• W3204133863 cites W3109154889 @default.
• W3204133863 cites W3180794345 @default.
• W3204133863 cites W77761613 @default.
• W3204133863 cites W2016462422 @default.
• W3204133863 doi "https://doi.org/10.48550/arxiv.2110.02948" @default.
• W3204133863 hasPublicationYear "2021" @default.
• W3204133863 type Work @default.
• W3204133863 sameAs 3204133863 @default.
• W3204133863 citedByCount "0" @default.
• W3204133863 crossrefType "posted-content" @default.
• W3204133863 hasAuthorship W3204133863A5003720426 @default.
• W3204133863 hasAuthorship W3204133863A5005369320 @default.
• W3204133863 hasAuthorship W3204133863A5006442099 @default.
• W3204133863 hasAuthorship W3204133863A5025958423 @default.
• W3204133863 hasAuthorship W3204133863A5032894412 @default.
• W3204133863 hasAuthorship W3204133863A5079732143 @default.
• W3204133863 hasBestOaLocation W32041338631 @default.
• W3204133863 hasConcept C104317684 @default.
• W3204133863 hasConcept C11413529 @default.
• W3204133863 hasConcept C121684516 @default.
• W3204133863 hasConcept C123149101 @default.
• W3204133863 hasConcept C154945302 @default.
• W3204133863 hasConcept C181095308 @default.
• W3204133863 hasConcept C185592680 @default.
• W3204133863 hasConcept C200585589 @default.
• W3204133863 hasConcept C205711294 @default.
• W3204133863 hasConcept C31487907 @default.
• W3204133863 hasConcept C31972630 @default.
• W3204133863 hasConcept C41008148 @default.
• W3204133863 hasConcept C55493867 @default.
• W3204133863 hasConcept C63479239 @default.
• W3204133863 hasConceptScore W3204133863C104317684 @default.
• W3204133863 hasConceptScore W3204133863C11413529 @default.

• next