3D Human Shape and Pose from a Single Depth Image with Deep Dense Correspondence Enabled Model Fitting

Simple item page
dc.contributor.authorWang, Xiaofangen_US
dc.contributor.authorBoukhayma, Adnaneen_US
dc.contributor.authorPrévost, Stéphanieen_US
dc.contributor.authorDesjardin, Ericen_US
dc.contributor.authorLoscos, Celineen_US
dc.contributor.authorMulton, Francken_US
dc.contributor.editorSauvage, Basileen_US
dc.contributor.editorHasic-Telalovic, Jasminkaen_US
dc.date.accessioned2022-04-22T07:54:27Z
dc.date.available2022-04-22T07:54:27Z
dc.date.issued2022
dc.description.abstractWe propose a two-stage hybrid method, with no initialization, for 3D human shape and pose estimation from a single depth image, combining the benefits of deep learning and optimization. First, a convolutional neural network predicts pixel-wise dense semantic correspondences to a template geometry, in the form of body part segmentation labels and normalized canonical geometry vertex coordinates. Using these two outputs, pixel-to-vertex correspondences are computed in a six-dimensional embedding of the template geometry through nearest neighbor. Second, a parametric shape model (SMPL) is fitted to the depth data by minimizing vertex distances to the input. Extensive evaluation on both real and synthetic human shape in motion datasets shows that our method yields quantitatively and qualitatively satisfactory results and state-of-the-art reconstruction errors.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEurographics 2022 - Posters
dc.identifier.doi10.2312/egp.20221008
dc.identifier.isbn978-3-03868-171-7
dc.identifier.issn1017-4656
dc.identifier.pages19-20
dc.identifier.pages2 pages
dc.identifier.urihttps://doi.org/10.2312/egp.20221008
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/egp20221008
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies --> Motion capture; Motion processing
dc.subjectComputing methodologies
dc.subjectMotion capture
dc.subjectMotion processing
dc.title3D Human Shape and Pose from a Single Depth Image with Deep Dense Correspondence Enabled Model Fittingen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
019-020.pdf
Size:
2.62 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
postereg2022_schedarvfinal.pdf
Size:
791.03 KB
Format:
Adobe Portable Document Format
Download
Collections
EG 2022 - Posters