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

Item

ITEM ACTIONSEXPORT

Released

Paper

Efficient Multi-view Performance Capture of Fine-Scale Surface Detail

MPS-Authors
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/persons43977

de Aguiar,  Edilson
Computer Graphics, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons44608

Helten,  Thomas
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:1602.02023.pdf
(Preprint), 5MB

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

Robertini, N., de Aguiar, E., Helten, T., & Theobalt, C. (2016). Efficient Multi-view Performance Capture of Fine-Scale Surface Detail. doi:10.1109/3DV.2014.46.


Cite as: http://hdl.handle.net/11858/00-001M-0000-002B-07CD-A
Abstract
We present a new effective way for performance capture of deforming meshes with fine-scale time-varying surface detail from multi-view video. Our method builds up on coarse 4D surface reconstructions, as obtained with commonly used template-based methods. As they only capture models of coarse-to-medium scale detail, fine scale deformation detail is often done in a second pass by using stereo constraints, features, or shading-based refinement. In this paper, we propose a new effective and stable solution to this second step. Our framework creates an implicit representation of the deformable mesh using a dense collection of 3D Gaussian functions on the surface, and a set of 2D Gaussians for the images. The fine scale deformation of all mesh vertices that maximizes photo-consistency can be efficiently found by densely optimizing a new model-to-image consistency energy on all vertex positions. A principal advantage is that our problem formulation yields a smooth closed form energy with implicit occlusion handling and analytic derivatives. Error-prone correspondence finding, or discrete sampling of surface displacement values are also not needed. We show several reconstructions of human subjects wearing loose clothing, and we qualitatively and quantitatively show that we robustly capture more detail than related methods.