Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204455263> ?p ?o ?g. }
- W3204455263 abstract "This paper addresses the challenge of reconstructing an animatable human model from a multi-view video. Some recent works have proposed to decompose a non-rigidly deforming scene into a canonical neural radiance field and a set of deformation fields that map observation-space points to the canonical space, thereby enabling them to learn the dynamic scene from images. However, they represent the deformation field as translational vector field or SE(3) field, which makes the optimization highly under-constrained. Moreover, these representations cannot be explicitly controlled by input motions. Instead, we introduce neural blend weight fields to produce the deformation fields. Based on the skeleton-driven deformation, blend weight fields are used with 3D human skeletons to generate observation-to-canonical and canonical-to-observation correspondences. Since 3D human skeletons are more observable, they can regularize the learning of deformation fields. Moreover, the learned blend weight fields can be combined with input skeletal motions to generate new deformation fields to animate the human model. Experiments show that our approach significantly outperforms recent human synthesis methods. The code and supplementary materials are available at https://zju3dv.github.io/animatable_nerf/." @default.
- W3204455263 created "2021-10-11" @default.
- W3204455263 creator A5006558591 @default.
- W3204455263 creator A5059021869 @default.
- W3204455263 creator A5059973746 @default.
- W3204455263 creator A5060815622 @default.
- W3204455263 creator A5062755510 @default.
- W3204455263 creator A5073087748 @default.
- W3204455263 creator A5084787269 @default.
- W3204455263 date "2021-05-06" @default.
- W3204455263 modified "2023-09-27" @default.
- W3204455263 title "Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies" @default.
- W3204455263 cites W1938204631 @default.
- W3204455263 cites W1993962870 @default.
- W3204455263 cites W2044618760 @default.
- W3204455263 cites W2055174129 @default.
- W3204455263 cites W2101032778 @default.
- W3204455263 cites W2138624212 @default.
- W3204455263 cites W2229412420 @default.
- W3204455263 cites W2235136907 @default.
- W3204455263 cites W2461005315 @default.
- W3204455263 cites W2768683308 @default.
- W3204455263 cites W2793768642 @default.
- W3204455263 cites W2798637590 @default.
- W3204455263 cites W2886799640 @default.
- W3204455263 cites W2921745007 @default.
- W3204455263 cites W2924060277 @default.
- W3204455263 cites W2942074357 @default.
- W3204455263 cites W2946584893 @default.
- W3204455263 cites W2962730651 @default.
- W3204455263 cites W2962819541 @default.
- W3204455263 cites W2962921964 @default.
- W3204455263 cites W2963073614 @default.
- W3204455263 cites W2963335855 @default.
- W3204455263 cites W2963515833 @default.
- W3204455263 cites W2963627347 @default.
- W3204455263 cites W2963907666 @default.
- W3204455263 cites W2963926543 @default.
- W3204455263 cites W2963995996 @default.
- W3204455263 cites W2964121744 @default.
- W3204455263 cites W2971278627 @default.
- W3204455263 cites W2971467054 @default.
- W3204455263 cites W2974180492 @default.
- W3204455263 cites W2978956737 @default.
- W3204455263 cites W2981978060 @default.
- W3204455263 cites W2984529706 @default.
- W3204455263 cites W2999408714 @default.
- W3204455263 cites W3034968345 @default.
- W3204455263 cites W3035191304 @default.
- W3204455263 cites W3035291735 @default.
- W3204455263 cites W3035492592 @default.
- W3204455263 cites W3035507572 @default.
- W3204455263 cites W3035515747 @default.
- W3204455263 cites W3035581100 @default.
- W3204455263 cites W3092203888 @default.
- W3204455263 cites W3095085713 @default.
- W3204455263 cites W3096718826 @default.
- W3204455263 cites W3100398946 @default.
- W3204455263 cites W3101022589 @default.
- W3204455263 cites W3105974636 @default.
- W3204455263 cites W3106171282 @default.
- W3204455263 cites W3107384982 @default.
- W3204455263 cites W3107486934 @default.
- W3204455263 cites W3108325989 @default.
- W3204455263 cites W3109376949 @default.
- W3204455263 cites W3109585842 @default.
- W3204455263 cites W3110496917 @default.
- W3204455263 cites W3119185462 @default.
- W3204455263 cites W3153220274 @default.
- W3204455263 cites W3174541392 @default.
- W3204455263 cites W3174752334 @default.
- W3204455263 cites W3176327543 @default.
- W3204455263 cites W3176762345 @default.
- W3204455263 cites W3177491479 @default.
- W3204455263 cites W3202753943 @default.
- W3204455263 cites W3203616647 @default.
- W3204455263 doi "https://doi.org/10.48550/arxiv.2105.02872" @default.
- W3204455263 hasPublicationYear "2021" @default.
- W3204455263 type Work @default.
- W3204455263 sameAs 3204455263 @default.
- W3204455263 citedByCount "1" @default.
- W3204455263 countsByYear W32044552632021 @default.
- W3204455263 crossrefType "posted-content" @default.
- W3204455263 hasAuthorship W3204455263A5006558591 @default.
- W3204455263 hasAuthorship W3204455263A5059021869 @default.
- W3204455263 hasAuthorship W3204455263A5059973746 @default.
- W3204455263 hasAuthorship W3204455263A5060815622 @default.
- W3204455263 hasAuthorship W3204455263A5062755510 @default.
- W3204455263 hasAuthorship W3204455263A5073087748 @default.
- W3204455263 hasAuthorship W3204455263A5084787269 @default.
- W3204455263 hasBestOaLocation W32044552631 @default.
- W3204455263 hasConcept C111919701 @default.
- W3204455263 hasConcept C11413529 @default.
- W3204455263 hasConcept C120665830 @default.
- W3204455263 hasConcept C121332964 @default.
- W3204455263 hasConcept C153294291 @default.
- W3204455263 hasConcept C154945302 @default.
- W3204455263 hasConcept C177264268 @default.
- W3204455263 hasConcept C199360897 @default.
- W3204455263 hasConcept C202444582 @default.