Matches in SemOpenAlex for { <https://semopenalex.org/work/W3181900527> ?p ?o ?g. }
- W3181900527 endingPage "15" @default.
- W3181900527 startingPage "1" @default.
- W3181900527 abstract "Animating a newly designed character using motion capture (mocap) data is a long standing problem in computer animation. A key consideration is the skeletal structure that should correspond to the available mocap data, and the shape deformation in the joint regions, which often requires a tailored, pose-specific refinement. In this work, we develop a neural technique for articulating 3D characters using enveloping with a pre-defined skeletal structure which produces high quality pose dependent deformations. Our framework learns to rig and skin characters with the same articulation structure (e.g., bipeds or quadrupeds), and builds the desired skeleton hierarchy into the network architecture. Furthermore, we propose neural blend shapes--a set of corrective pose-dependent shapes which improve the deformation quality in the joint regions in order to address the notorious artifacts resulting from standard rigging and skinning. Our system estimates neural blend shapes for input meshes with arbitrary connectivity, as well as weighting coefficients which are conditioned on the input joint rotations. Unlike recent deep learning techniques which supervise the network with ground-truth rigging and skinning parameters, our approach does not assume that the training data has a specific underlying deformation model. Instead, during training, the network observes deformed shapes and learns to infer the corresponding rig, skin and blend shapes using indirect supervision. During inference, we demonstrate that our network generalizes to unseen characters with arbitrary mesh connectivity, including unrigged characters built by 3D artists. Conforming to standard skeletal animation models enables direct plug-and-play in standard animation software, as well as game engines." @default.
- W3181900527 created "2021-07-19" @default.
- W3181900527 creator A5009881746 @default.
- W3181900527 creator A5010714340 @default.
- W3181900527 creator A5022318529 @default.
- W3181900527 creator A5038988704 @default.
- W3181900527 creator A5064927253 @default.
- W3181900527 creator A5074550197 @default.
- W3181900527 date "2021-07-19" @default.
- W3181900527 modified "2023-10-10" @default.
- W3181900527 title "Learning skeletal articulations with neural blend shapes" @default.
- W3181900527 cites W1604661281 @default.
- W3181900527 cites W1967554269 @default.
- W3181900527 cites W1982137976 @default.
- W3181900527 cites W1988200254 @default.
- W3181900527 cites W1991359153 @default.
- W3181900527 cites W1993962870 @default.
- W3181900527 cites W2012089397 @default.
- W3181900527 cites W2038198107 @default.
- W3181900527 cites W2040703987 @default.
- W3181900527 cites W2047417391 @default.
- W3181900527 cites W2055174129 @default.
- W3181900527 cites W2056316267 @default.
- W3181900527 cites W2071643746 @default.
- W3181900527 cites W2133607347 @default.
- W3181900527 cites W2136916831 @default.
- W3181900527 cites W2137267908 @default.
- W3181900527 cites W2144008209 @default.
- W3181900527 cites W2152005648 @default.
- W3181900527 cites W2157492339 @default.
- W3181900527 cites W2160692760 @default.
- W3181900527 cites W2293404936 @default.
- W3181900527 cites W2465121220 @default.
- W3181900527 cites W2472407021 @default.
- W3181900527 cites W2810984579 @default.
- W3181900527 cites W2891396148 @default.
- W3181900527 cites W2891959861 @default.
- W3181900527 cites W2979283733 @default.
- W3181900527 cites W3035024952 @default.
- W3181900527 cites W3048366741 @default.
- W3181900527 cites W3048473624 @default.
- W3181900527 cites W3048496284 @default.
- W3181900527 cites W3083703704 @default.
- W3181900527 cites W3101027576 @default.
- W3181900527 cites W3122282950 @default.
- W3181900527 cites W3136375062 @default.
- W3181900527 cites W3137158176 @default.
- W3181900527 cites W4235459551 @default.
- W3181900527 doi "https://doi.org/10.1145/3450626.3459852" @default.
- W3181900527 hasPublicationYear "2021" @default.
- W3181900527 type Work @default.
- W3181900527 sameAs 3181900527 @default.
- W3181900527 citedByCount "40" @default.
- W3181900527 countsByYear W31819005272020 @default.
- W3181900527 countsByYear W31819005272021 @default.
- W3181900527 countsByYear W31819005272022 @default.
- W3181900527 countsByYear W31819005272023 @default.
- W3181900527 crossrefType "journal-article" @default.
- W3181900527 hasAuthorship W3181900527A5009881746 @default.
- W3181900527 hasAuthorship W3181900527A5010714340 @default.
- W3181900527 hasAuthorship W3181900527A5022318529 @default.
- W3181900527 hasAuthorship W3181900527A5038988704 @default.
- W3181900527 hasAuthorship W3181900527A5064927253 @default.
- W3181900527 hasAuthorship W3181900527A5074550197 @default.
- W3181900527 hasBestOaLocation W31819005272 @default.
- W3181900527 hasConcept C104114177 @default.
- W3181900527 hasConcept C121684516 @default.
- W3181900527 hasConcept C127413603 @default.
- W3181900527 hasConcept C146849305 @default.
- W3181900527 hasConcept C154945302 @default.
- W3181900527 hasConcept C170154142 @default.
- W3181900527 hasConcept C18555067 @default.
- W3181900527 hasConcept C2777685762 @default.
- W3181900527 hasConcept C31487907 @default.
- W3181900527 hasConcept C31972630 @default.
- W3181900527 hasConcept C41008148 @default.
- W3181900527 hasConcept C48007421 @default.
- W3181900527 hasConcept C502989409 @default.
- W3181900527 hasConcept C50644808 @default.
- W3181900527 hasConcept C69369342 @default.
- W3181900527 hasConcept C78519656 @default.
- W3181900527 hasConceptScore W3181900527C104114177 @default.
- W3181900527 hasConceptScore W3181900527C121684516 @default.
- W3181900527 hasConceptScore W3181900527C127413603 @default.
- W3181900527 hasConceptScore W3181900527C146849305 @default.
- W3181900527 hasConceptScore W3181900527C154945302 @default.
- W3181900527 hasConceptScore W3181900527C170154142 @default.
- W3181900527 hasConceptScore W3181900527C18555067 @default.
- W3181900527 hasConceptScore W3181900527C2777685762 @default.
- W3181900527 hasConceptScore W3181900527C31487907 @default.
- W3181900527 hasConceptScore W3181900527C31972630 @default.
- W3181900527 hasConceptScore W3181900527C41008148 @default.
- W3181900527 hasConceptScore W3181900527C48007421 @default.
- W3181900527 hasConceptScore W3181900527C502989409 @default.
- W3181900527 hasConceptScore W3181900527C50644808 @default.
- W3181900527 hasConceptScore W3181900527C69369342 @default.
- W3181900527 hasConceptScore W3181900527C78519656 @default.
- W3181900527 hasIssue "4" @default.