FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3166229844> ?p ?o ?g. }

• W3166229844 abstract "We present SCANimate, an end-to-end trainable framework that takes raw 3D scans of a clothed human and turns them into an animatable avatar. These avatars are driven by pose parameters and have realistic clothing that moves and deforms naturally. SCANimate does not rely on a customized mesh template or surface mesh registration. We observe that fitting a parametric 3D body model, like SMPL, to a clothed human scan is tractable while surface registration of the body topology to the scan is often not, because clothing can deviate significantly from the body shape. We also observe that articulated transformations are invertible, resulting in geometric cycle-consistency in the posed and unposed shapes. These observations lead us to a weakly supervised learning method that aligns scans into a canonical pose by disentangling articulated deformations without template-based surface registration. Furthermore, to complete missing regions in the aligned scans while modeling pose-dependent deformations, we introduce a locally pose-aware implicit function that learns to complete and model geometry with learned pose correctives. In contrast to commonly used global pose embeddings, our local pose conditioning significantly reduces long-range spurious correlations and improves generalization to unseen poses, especially when training data is limited. Our method can be applied to pose-aware appearance modeling to generate a fully textured avatar. We demonstrate our approach on various clothing types with different amounts of training data, outperforming existing solutions and other variants in terms of fidelity and generality in every setting. The code is available at https://scanimate.is.tue.mpg.de." @default.
• W3166229844 created "2021-06-22" @default.
• W3166229844 creator A5040277267 @default.
• W3166229844 creator A5062785485 @default.
• W3166229844 creator A5065396778 @default.
• W3166229844 creator A5076609933 @default.
• W3166229844 date "2021-06-01" @default.
• W3166229844 modified "2023-10-16" @default.
• W3166229844 title "SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks" @default.
• W3166229844 cites W1520005879 @default.
• W3166229844 cites W1562699689 @default.
• W3166229844 cites W1967494143 @default.
• W3166229844 cites W1967554269 @default.
• W3166229844 cites W1971613390 @default.
• W3166229844 cites W1978216348 @default.
• W3166229844 cites W1989191365 @default.
• W3166229844 cites W1993962870 @default.
• W3166229844 cites W2052728883 @default.
• W3166229844 cites W2056316267 @default.
• W3166229844 cites W2060784870 @default.
• W3166229844 cites W2071663264 @default.
• W3166229844 cites W2071839134 @default.
• W3166229844 cites W2229412420 @default.
• W3166229844 cites W2483862638 @default.
• W3166229844 cites W2518246072 @default.
• W3166229844 cites W2545173102 @default.
• W3166229844 cites W2573098616 @default.
• W3166229844 cites W2596210417 @default.
• W3166229844 cites W2607760177 @default.
• W3166229844 cites W2737762407 @default.
• W3166229844 cites W2768683308 @default.
• W3166229844 cites W2793768642 @default.
• W3166229844 cites W2797515701 @default.
• W3166229844 cites W2798600195 @default.
• W3166229844 cites W2883221003 @default.
• W3166229844 cites W2886416285 @default.
• W3166229844 cites W2887586359 @default.
• W3166229844 cites W2921745007 @default.
• W3166229844 cites W2958623495 @default.
• W3166229844 cites W2962793481 @default.
• W3166229844 cites W2962849139 @default.
• W3166229844 cites W2963627347 @default.
• W3166229844 cites W2963669509 @default.
• W3166229844 cites W2963926543 @default.
• W3166229844 cites W2963995996 @default.
• W3166229844 cites W2964219767 @default.
• W3166229844 cites W2975420824 @default.
• W3166229844 cites W2978956737 @default.
• W3166229844 cites W2979283733 @default.
• W3166229844 cites W2981637078 @default.
• W3166229844 cites W2981657250 @default.
• W3166229844 cites W2981827368 @default.
• W3166229844 cites W2981978060 @default.
• W3166229844 cites W2984210651 @default.
• W3166229844 cites W2990863967 @default.
• W3166229844 cites W2991621301 @default.
• W3166229844 cites W2997477328 @default.
• W3166229844 cites W2997691263 @default.
• W3166229844 cites W3034757648 @default.
• W3166229844 cites W3035291735 @default.
• W3166229844 cites W3035396254 @default.
• W3166229844 cites W3035492592 @default.
• W3166229844 cites W3035507572 @default.
• W3166229844 cites W3035591705 @default.
• W3166229844 cites W3048496284 @default.
• W3166229844 cites W3049667295 @default.
• W3166229844 cites W3107290753 @default.
• W3166229844 cites W3107471220 @default.
• W3166229844 cites W3107812413 @default.
• W3166229844 cites W3138581055 @default.
• W3166229844 doi "https://doi.org/10.1109/cvpr46437.2021.00291" @default.
• W3166229844 hasPublicationYear "2021" @default.
• W3166229844 type Work @default.
• W3166229844 sameAs 3166229844 @default.
• W3166229844 citedByCount "96" @default.
• W3166229844 countsByYear W31662298442021 @default.
• W3166229844 countsByYear W31662298442022 @default.
• W3166229844 countsByYear W31662298442023 @default.
• W3166229844 crossrefType "proceedings-article" @default.
• W3166229844 hasAuthorship W3166229844A5040277267 @default.
• W3166229844 hasAuthorship W3166229844A5062785485 @default.
• W3166229844 hasAuthorship W3166229844A5065396778 @default.
• W3166229844 hasAuthorship W3166229844A5076609933 @default.
• W3166229844 hasBestOaLocation W31662298442 @default.
• W3166229844 hasConcept C107457646 @default.
• W3166229844 hasConcept C11413529 @default.
• W3166229844 hasConcept C119857082 @default.
• W3166229844 hasConcept C134306372 @default.
• W3166229844 hasConcept C154945302 @default.
• W3166229844 hasConcept C177148314 @default.
• W3166229844 hasConcept C2777365542 @default.
• W3166229844 hasConcept C31972630 @default.
• W3166229844 hasConcept C33923547 @default.
• W3166229844 hasConcept C41008148 @default.
• W3166229844 hasConcept C52102323 @default.
• W3166229844 hasConcept C97256817 @default.
• W3166229844 hasConceptScore W3166229844C107457646 @default.
• W3166229844 hasConceptScore W3166229844C11413529 @default.
• W3166229844 hasConceptScore W3166229844C119857082 @default.
• W3166229844 hasConceptScore W3166229844C134306372 @default.

• next