Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044960031> ?p ?o ?g. }
- W3044960031 abstract "Parametric models of humans, faces, hands and animals have been widely used for a range of tasks such as image-based reconstruction, shape correspondence estimation, and animation. Their key strength is the ability to factor surface variations into shape and pose dependent components. Learning such models requires lots of expert knowledge and hand-defined object-specific constraints, making the learning approach unscalable to novel objects. In this paper, we present a simple yet effective approach to learn disentangled shape and pose representations in an unsupervised setting. We use a combination of self-consistency and cross-consistency constraints to learn pose and shape space from registered meshes. We additionally incorporate as-rigid-as-possible deformation(ARAP) into the training loop to avoid degenerate solutions. We demonstrate the usefulness of learned representations through a number of tasks including pose transfer and shape retrieval. The experiments on datasets of 3D humans, faces, hands and animals demonstrate the generality of our approach. Code is made available at https://virtualhumans.mpi-inf.mpg.de/unsup_shape_pose/." @default.
- W3044960031 created "2020-07-29" @default.
- W3044960031 creator A5016068029 @default.
- W3044960031 creator A5054279864 @default.
- W3044960031 creator A5076908763 @default.
- W3044960031 date "2020-07-22" @default.
- W3044960031 modified "2023-09-27" @default.
- W3044960031 title "Unsupervised Shape and Pose Disentanglement for 3D Meshes" @default.
- W3044960031 cites W1967554269 @default.
- W3044960031 cites W1988874269 @default.
- W3044960031 cites W1989191365 @default.
- W3044960031 cites W2035433457 @default.
- W3044960031 cites W2049462432 @default.
- W3044960031 cites W2107037917 @default.
- W3044960031 cites W2122007052 @default.
- W3044960031 cites W2151636374 @default.
- W3044960031 cites W2419474014 @default.
- W3044960031 cites W2555859288 @default.
- W3044960031 cites W2559823555 @default.
- W3044960031 cites W2753738274 @default.
- W3044960031 cites W2767614780 @default.
- W3044960031 cites W2768683308 @default.
- W3044960031 cites W2769666294 @default.
- W3044960031 cites W2883221003 @default.
- W3044960031 cites W2883758202 @default.
- W3044960031 cites W2890663137 @default.
- W3044960031 cites W2902035653 @default.
- W3044960031 cites W2904922784 @default.
- W3044960031 cites W2917887692 @default.
- W3044960031 cites W2944407796 @default.
- W3044960031 cites W2945820757 @default.
- W3044960031 cites W2948200197 @default.
- W3044960031 cites W2962793481 @default.
- W3044960031 cites W2962928839 @default.
- W3044960031 cites W2963022858 @default.
- W3044960031 cites W2963045453 @default.
- W3044960031 cites W2963104724 @default.
- W3044960031 cites W2963129901 @default.
- W3044960031 cites W2963226019 @default.
- W3044960031 cites W2963475767 @default.
- W3044960031 cites W2963515833 @default.
- W3044960031 cites W2964127395 @default.
- W3044960031 cites W2970263573 @default.
- W3044960031 cites W2971856312 @default.
- W3044960031 cites W2974403539 @default.
- W3044960031 cites W2982697283 @default.
- W3044960031 cites W2985832137 @default.
- W3044960031 cites W2992956318 @default.
- W3044960031 cites W3000817459 @default.
- W3044960031 cites W3008956107 @default.
- W3044960031 cites W3019382938 @default.
- W3044960031 cites W3114458132 @default.
- W3044960031 cites W603908379 @default.
- W3044960031 doi "https://doi.org/10.48550/arxiv.2007.11341" @default.
- W3044960031 hasPublicationYear "2020" @default.
- W3044960031 type Work @default.
- W3044960031 sameAs 3044960031 @default.
- W3044960031 citedByCount "0" @default.
- W3044960031 crossrefType "posted-content" @default.
- W3044960031 hasAuthorship W3044960031A5016068029 @default.
- W3044960031 hasAuthorship W3044960031A5054279864 @default.
- W3044960031 hasAuthorship W3044960031A5076908763 @default.
- W3044960031 hasBestOaLocation W30449600311 @default.
- W3044960031 hasConcept C105795698 @default.
- W3044960031 hasConcept C111919701 @default.
- W3044960031 hasConcept C117251300 @default.
- W3044960031 hasConcept C119857082 @default.
- W3044960031 hasConcept C121684516 @default.
- W3044960031 hasConcept C129641003 @default.
- W3044960031 hasConcept C153180895 @default.
- W3044960031 hasConcept C154945302 @default.
- W3044960031 hasConcept C15744967 @default.
- W3044960031 hasConcept C159985019 @default.
- W3044960031 hasConcept C177264268 @default.
- W3044960031 hasConcept C192562407 @default.
- W3044960031 hasConcept C199360897 @default.
- W3044960031 hasConcept C204323151 @default.
- W3044960031 hasConcept C2776436953 @default.
- W3044960031 hasConcept C2776760102 @default.
- W3044960031 hasConcept C2778572836 @default.
- W3044960031 hasConcept C2780767217 @default.
- W3044960031 hasConcept C2781238097 @default.
- W3044960031 hasConcept C31487907 @default.
- W3044960031 hasConcept C31972630 @default.
- W3044960031 hasConcept C33923547 @default.
- W3044960031 hasConcept C41008148 @default.
- W3044960031 hasConcept C52102323 @default.
- W3044960031 hasConcept C542102704 @default.
- W3044960031 hasConcept C89600930 @default.
- W3044960031 hasConceptScore W3044960031C105795698 @default.
- W3044960031 hasConceptScore W3044960031C111919701 @default.
- W3044960031 hasConceptScore W3044960031C117251300 @default.
- W3044960031 hasConceptScore W3044960031C119857082 @default.
- W3044960031 hasConceptScore W3044960031C121684516 @default.
- W3044960031 hasConceptScore W3044960031C129641003 @default.
- W3044960031 hasConceptScore W3044960031C153180895 @default.
- W3044960031 hasConceptScore W3044960031C154945302 @default.
- W3044960031 hasConceptScore W3044960031C15744967 @default.
- W3044960031 hasConceptScore W3044960031C159985019 @default.
- W3044960031 hasConceptScore W3044960031C177264268 @default.