Sorry, you need to enable JavaScript to visit this website.

Stereoscopic Multiview and 3D Processing

BODYFITR: Robust automatic 3D human body fitting


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.

Paper Details

Authors:
Submitted On:
19 September 2019 - 12:58pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

bodyfitr poster

(15)

Subscribe

[1] , "BODYFITR: Robust automatic 3D human body fitting", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4744. Accessed: Nov. 15, 2019.
@article{4744-19,
url = {http://sigport.org/4744},
author = { },
publisher = {IEEE SigPort},
title = {BODYFITR: Robust automatic 3D human body fitting},
year = {2019} }
TY - EJOUR
T1 - BODYFITR: Robust automatic 3D human body fitting
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4744
ER -
. (2019). BODYFITR: Robust automatic 3D human body fitting. IEEE SigPort. http://sigport.org/4744
, 2019. BODYFITR: Robust automatic 3D human body fitting. Available at: http://sigport.org/4744.
. (2019). "BODYFITR: Robust automatic 3D human body fitting." Web.
1. . BODYFITR: Robust automatic 3D human body fitting [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4744

GLOBAL MULTIVIEW REGISTRATION USING NON-CONVEX ADMM


We consider the problem of aligning multiview scans obtained using
a range scanner. The computational pipeline for this problem can be
divided into two phases: (i) finding point-to-point correspondences
between overlapping scans, and (ii) registration of the scans based
on the found correspondences. The focus of this work is on global
registration in which the scans (modeled as point clouds) are required
to be jointly registered in a common reference frame. We consider
an optimization framework for global registration that is based on

Paper Details

Authors:
Kunal N. Chaudhury
Submitted On:
14 September 2017 - 7:08am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

slides.pdf

(619)

Keywords

Additional Categories

Subscribe

[1] Kunal N. Chaudhury, "GLOBAL MULTIVIEW REGISTRATION USING NON-CONVEX ADMM", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2015. Accessed: Nov. 15, 2019.
@article{2015-17,
url = {http://sigport.org/2015},
author = {Kunal N. Chaudhury },
publisher = {IEEE SigPort},
title = {GLOBAL MULTIVIEW REGISTRATION USING NON-CONVEX ADMM},
year = {2017} }
TY - EJOUR
T1 - GLOBAL MULTIVIEW REGISTRATION USING NON-CONVEX ADMM
AU - Kunal N. Chaudhury
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2015
ER -
Kunal N. Chaudhury. (2017). GLOBAL MULTIVIEW REGISTRATION USING NON-CONVEX ADMM. IEEE SigPort. http://sigport.org/2015
Kunal N. Chaudhury, 2017. GLOBAL MULTIVIEW REGISTRATION USING NON-CONVEX ADMM. Available at: http://sigport.org/2015.
Kunal N. Chaudhury. (2017). "GLOBAL MULTIVIEW REGISTRATION USING NON-CONVEX ADMM." Web.
1. Kunal N. Chaudhury. GLOBAL MULTIVIEW REGISTRATION USING NON-CONVEX ADMM [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2015