Reference : 3DBooSTeR: 3D Body Shape and Texture Recovery
Scientific congresses, symposiums and conference proceedings : Unpublished conference
Engineering, computing & technology : Computer science
Computational Sciences
http://hdl.handle.net/10993/44702
3DBooSTeR: 3D Body Shape and Texture Recovery
English
Saint, Alexandre Fabian A mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
Kacem, Anis mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
Cherenkova, Kseniya mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Aouada, Djamila mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
23-Aug-2020
We propose 3DBooSTeR, a novel method to recover a textured 3D body mesh from a textured partial 3D scan. With the advent of virtual and augmented reality, there is a demand for creating realistic and high-fidelity digital 3D human representations. However, 3D scanning systems can only capture the 3D human body shape up to some level of defects due to its complexity, including occlusion between bodyparts, varying levels of details, shape deformations, and the articulated skeleton. Textured 3D mesh completion is thus important to enhance3D acquisitions. The proposed approach decouples the shape and texture completion into two sequential tasks. The shape is recovered by an encoder-decoder network deforming a template body mesh. The texture is subsequently obtained by projecting the partial texture onto the template mesh before inpainting the corresponding texture map with a novel approach. The approach is validated on the 3DBodyTex.v2 dataset.
Yes
International
SHARP workshop, ECCV 2020
23-08-2020
[en] 3D shape completion ; Human body shape ; Point cloud
[en] We propose 3DBooSTeR, a novel method to recover a textured 3D body mesh from a textured partial 3D scan. With the advent of virtual and augmented reality, there is a demand for creating realistic and high-fidelity digital 3D human representations. However, 3D scanning systems can only capture the 3D human body shape up to some level of defects due to its complexity, including occlusion between bodyparts, varying levels of details, shape deformations and the articulated skeleton. Textured 3D mesh completion is thus important to enhance3D acquisitions. The proposed approach decouples the shape and texture completion into two sequential tasks. The shape is recovered by an encoder-decoder network deforming a template body mesh. The texture is subsequently obtained by projecting the partial texture onto the template mesh before inpainting the corresponding texture map with a novel approach. The approach is validated on the 3DBodyTex.v2 dataset
http://hdl.handle.net/10993/44702
FnR ; FNR11806282 > Alexandre Saint > > Accurate 3D human body shape modelling and fitting under clothing > 01/09/2017 > 14/01/2021 > 2017

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
3DBooster_SHARP_ECCV20.pdfPublisher postprint27.26 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.