Scipediacontent: Scipediacontent moved page Draft Content 838265898 to Cherenkova et al 2019a

2021-01-28T21:48:45Z

Scipediacontent moved page Draft Content 838265898 to Cherenkova et al 2019a

Scipediacontent: Created page with " == Abstract == This paper proposes BODYFITR, a fully automatic method to fit a human body model to static 3D scans with complex poses. Automatic and reliable 3D human body f..."

2021-01-28T21:48:40Z

Created page with " == Abstract == This paper proposes BODYFITR, a fully automatic method to fit a human body model to static 3D scans with complex poses. Automatic and reliable 3D human body f..."

New page

== Abstract ==

This paper proposes BODYFITR, a fully automatic method to fit a human body model to static 3D scans with complex poses. Automatic and reliable 3D human body fitting is necessary for many applications related to healthcare, digital ergonomics, avatar creation and security, especially in industrial contexts for large-scale product design. Existing works either make prior assumptions on the pose, require manual annotation of the data or have difficulty handling complex poses. This work addresses these limitations by providing a novel automatic fitting pipeline with carefully integrated building blocks designed for a systematic and robust approach. It is validated on the 3DBodyTex dataset, with hundreds of high-quality 3D body scans, and shown to outperform prior works in static body pose and shape estimation, qualitatively and quantitatively. The method is also applied to the creation of realistic 3D avatars from the high-quality texture scans of 3DBodyTex, further demonstrating its capabilities.

== Original document ==

The different versions of the original document can be found in:

* [https://orbilu.uni.lu/bitstream/10993/40439/2/saint_bodyfitr_icip2019.pdf https://orbilu.uni.lu/bitstream/10993/40439/2/saint_bodyfitr_icip2019.pdf] under the license https://creativecommons.org/licenses/by-nc-sa

* [http://xplorestaging.ieee.org/ielx7/8791230/8799366/08803819.pdf?arnumber=8803819 http://xplorestaging.ieee.org/ielx7/8791230/8799366/08803819.pdf?arnumber=8803819],
: [http://dx.doi.org/10.1109/icip.2019.8803819 http://dx.doi.org/10.1109/icip.2019.8803819] under the license cc-by-nc-sa

* [https://cvdatasets.uni.lu https://cvdatasets.uni.lu],
: [http://orbilu.uni.lu/handle/10993/40439 http://orbilu.uni.lu/handle/10993/40439]

* [https://dblp.uni-trier.de/db/conf/icip/icip2019.html#SaintSCGAO19 https://dblp.uni-trier.de/db/conf/icip/icip2019.html#SaintSCGAO19],
: [https://orbilu.uni.lu/handle/10993/40439 https://orbilu.uni.lu/handle/10993/40439],
: [https://sigport.org/documents/bodyfitr-robust-automatic-3d-human-body-fitting https://sigport.org/documents/bodyfitr-robust-automatic-3d-human-body-fitting],
: [https://orbilu.uni.lu/bitstream/10993/40439/2/saint_bodyfitr_icip2019.pdf https://orbilu.uni.lu/bitstream/10993/40439/2/saint_bodyfitr_icip2019.pdf],
: [https://academic.microsoft.com/#/detail/2971103666 https://academic.microsoft.com/#/detail/2971103666]

← Older revision	Revision as of 21:48, 28 January 2021
(No difference)

Cherenkova et al 2019a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 838265898 to Cherenkova et al 2019a

Scipediacontent: Created page with " == Abstract == This paper proposes BODYFITR, a fully automatic method to fit a human body model to static 3D scans with complex poses. Automatic and reliable 3D human body f..."