DeformSyncNet: Deformation Transfer via Synchronized Shape Deformation Spaces

Cited 4 time in webofscience Cited 4 time in scopus
  • Hit : 261
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorSung, Minhyukko
dc.contributor.authorJiang, Zhenyuko
dc.contributor.authorAchlioptas, Panosko
dc.contributor.authorMitra, Niloy J.ko
dc.contributor.authorGuibas, Leonidasko
dc.date.accessioned2021-02-23T02:50:05Z-
dc.date.available2021-02-23T02:50:05Z-
dc.date.created2021-02-23-
dc.date.created2021-02-23-
dc.date.created2021-02-23-
dc.date.issued2020-12-
dc.identifier.citationACM TRANSACTIONS ON GRAPHICS, v.39, no.6, pp.261-
dc.identifier.issn0730-0301-
dc.identifier.urihttp://hdl.handle.net/10203/280982-
dc.description.abstractShape deformation is an important component in any geometry processing toolbox. The goal is to enable intuitive deformations of single or multiple shapes or to transfer example deformations to new shapes while preserving the plausibility of the deformed shape(s). Existing approaches assume access to point-level or part-level correspondence or establish them in a preprocessing phase, thus limiting the scope and generality of such approaches. We propose DEFORMSYNCNET, a new approach that allows consistent and synchronized shape deformations without requiring explicit correspondence information. Technically, we achieve this by encoding deformations into a class-specific idealized latent space while decoding them into an individual, model-specific linear deformation action space, operating directly in 3D. The underlying encoding and decoding are performed by specialized (jointly trained) neural networks. By design, the inductive bias of our networks results in a deformation space with several desirable properties, such as path invariance across different deformation pathways, which are then also approximately preserved in real space. We qualitatively and quantitatively evaluate our framework against multiple alternative approaches and demonstrate improved performance.-
dc.languageEnglish-
dc.publisherASSOC COMPUTING MACHINERY-
dc.titleDeformSyncNet: Deformation Transfer via Synchronized Shape Deformation Spaces-
dc.typeArticle-
dc.identifier.wosid000595589100101-
dc.identifier.scopusid2-s2.0-85097331262-
dc.type.rimsART-
dc.citation.volume39-
dc.citation.issue6-
dc.citation.beginningpage261-
dc.citation.publicationnameACM TRANSACTIONS ON GRAPHICS-
dc.identifier.doi10.1145/3414685.3417783-
dc.contributor.localauthorSung, Minhyuk-
dc.contributor.nonIdAuthorJiang, Zhenyu-
dc.contributor.nonIdAuthorAchlioptas, Panos-
dc.contributor.nonIdAuthorMitra, Niloy J.-
dc.contributor.nonIdAuthorGuibas, Leonidas-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorDeformation-
dc.subject.keywordAuthorDeformation Transfer-
dc.subject.keywordAuthorShape Editing-
dc.subject.keywordAuthorShape Embedding-
dc.subject.keywordAuthor3D Deep Learning-
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 4 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0