English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Efficient Multi-view Performance Capture of Fine-Scale Surface Detail

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.

Item is

Files

show Files
hide Files
:
arXiv:1602.02023.pdf (Preprint), 5MB
Name:
arXiv:1602.02023.pdf
Description:
File downloaded from arXiv at 2016-07-18 11:37
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Robertini, Nadia1, Author           
de Aguiar, Edilson1, Author           
Helten, Thomas1, Author           
Theobalt, Christian1, Author                 
Affiliations:
1Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR
 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.

Details

show
hide
Language(s): eng - English
 Dates: 2016-02-052016
 Publication Status: Published online
 Pages: 9 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1602.02023
DOI: 10.1109/3DV.2014.46
URI: http://arxiv.org/abs/1602.02023
BibTex Citekey: Robertini_arXiv2016
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show