de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons79450

Rhodin,  Helge
Computer Graphics, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons79452

Robertini,  Nadia
Computer Graphics, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons138534

Casas,  Dan
Computer Graphics, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45289

Richardt,  Christian
Computer Graphics, MPI for Informatics, Max Planck Society;
Intel Visual Computing Institute;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45449

Seidel,  Hans-Peter
Computer Graphics, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45610

Theobalt,  Christian
Computer Graphics, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1607.08659.pdf
(Preprint), 5MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Rhodin, H., Robertini, N., Casas, D., Richardt, C., Seidel, H.-P., & Theobalt, C. (2016). General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues. Retrieved from http://arxiv.org/abs/1607.08659.


Cite as: http://hdl.handle.net/11858/00-001M-0000-002B-9883-C
Abstract
Markerless motion capture algorithms require a 3D body with properly personalized skeleton dimension and/or body shape and appearance to successfully track a person. Unfortunately, many tracking methods consider model personalization a different problem and use manual or semi-automatic model initialization, which greatly reduces applicability. In this paper, we propose a fully automatic algorithm that jointly creates a rigged actor model commonly used for animation - skeleton, volumetric shape, appearance, and optionally a body surface - and estimates the actor's motion from multi-view video input only. The approach is rigorously designed to work on footage of general outdoor scenes recorded with very few cameras and without background subtraction. Our method uses a new image formation model with analytic visibility and analytically differentiable alignment energy. For reconstruction, 3D body shape is approximated as Gaussian density field. For pose and shape estimation, we minimize a new edge-based alignment energy inspired by volume raycasting in an absorbing medium. We further propose a new statistical human body model that represents the body surface, volumetric Gaussian density, as well as variability in skeleton shape. Given any multi-view sequence, our method jointly optimizes the pose and shape parameters of this model fully automatically in a spatiotemporal way.