Publication:
Deep generation of 3D articulated models and animations from 2D stick figures

dc.contributor.coauthorAkman, Alican
dc.contributor.coauthorSahillioğlu, Yusuf
dc.contributor.departmentDepartment of Computer Engineering
dc.contributor.kuauthorSezgin, Tevfik Metin
dc.contributor.schoolcollegeinstituteCollege of Engineering
dc.date.accessioned2024-11-09T12:44:20Z
dc.date.issued2022
dc.description.abstractGenerating 3D models from 2D images or sketches is a widely studied important problem in computer graphics. We describe the first method to generate a 3D human model from a single sketched stick figure. In contrast to the existing human modeling techniques, our method does not require a statistical body shape model. We exploit Variational Autoencoders to develop a novel framework capable of transitioning from a simple 2D stick figure sketch, to a corresponding 3D human model. Our network learns the mapping between the input sketch and the output 3D model. Furthermore, our model learns the embedding space around these models. We demonstrate that our network can generate not only 3D models, but also 3D animations through interpolation and extrapolation in the learned embedding space. In addition to 3D human models, we produce 3D horse models in order to show the generalization ability of our framework. Extensive experiments show that our model learns to generate compatible 3D models and animations with 2D sketches.
dc.description.fulltextYES
dc.description.indexedbyWOS
dc.description.indexedbyScopus
dc.description.openaccessYES
dc.description.publisherscopeInternational
dc.description.sponsoredbyTubitakEuEU - TÜBİTAK
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TÜBİTAK)
dc.description.sponsorshipEuropean Union (EU)
dc.description.sponsorshipEuropean Commission (EC)
dc.description.sponsorshipERA-NET Program
dc.description.sponsorshipThe IMOTION project
dc.description.versionPublisher version
dc.description.volume109
dc.identifier.doi10.1016/j.cag.2022.10.004
dc.identifier.eissn1873-7684
dc.identifier.embargoNO
dc.identifier.filenameinventorynoIR04067
dc.identifier.issn0097-8493
dc.identifier.quartileQ2
dc.identifier.scopus2-s2.0-85141316733
dc.identifier.urihttps://hdl.handle.net/20.500.14288/2397
dc.identifier.wos882443100003
dc.keywordsComputer graphics
dc.keywords3D model generation
dc.keywordsDeep learning
dc.keywordsSketch-based shape modeling
dc.language.isoeng
dc.publisherElsevier
dc.relation.grantnoEEEAG-115E471
dc.relation.grantnoEEEAG-119E572
dc.relation.ispartofComputers and Graphics
dc.relation.urihttp://cdm21054.contentdm.oclc.org/cdm/ref/collection/IR/id/10948
dc.subjectComputer science
dc.subjectSoftware engineering
dc.titleDeep generation of 3D articulated models and animations from 2D stick figures
dc.typeJournal Article
dspace.entity.typePublication
local.contributor.kuauthorSezgin, Tevfik Metin
local.publication.orgunit1College of Engineering
local.publication.orgunit2Department of Computer Engineering
relation.isOrgUnitOfPublication89352e43-bf09-4ef4-82f6-6f9d0174ebae
relation.isOrgUnitOfPublication.latestForDiscovery89352e43-bf09-4ef4-82f6-6f9d0174ebae
relation.isParentOrgUnitOfPublication8e756b23-2d4a-4ce8-b1b3-62c794a8c164
relation.isParentOrgUnitOfPublication.latestForDiscovery8e756b23-2d4a-4ce8-b1b3-62c794a8c164

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
10948.pdf
Size:
1.99 MB
Format:
Adobe Portable Document Format