Home News About Us Contact Contributors Disclaimer Privacy Policy Help FAQ

Home
Search
Quick Search
Advanced
Fulltext
Browse
Collections
Persons
My eDoc
Session History
Login
Name:
Password:
Documentation
Help
Support Wiki
Direct access to
document ID:


          Institute: MPI für Informatik     Collection: Computer Graphics Group     Display Documents



ID: 427960.0, MPI für Informatik / Computer Graphics Group
Dense Correspondence Finding for Parametrization-free Animation Reconstruction from Video
Authors:Ahmed, Naveed; Theobalt, Christian; Rössl, Christian; Thrun, Sebastian; Seidel, Hans-Peter
Language:English
Publisher:IEEE Computer Society
Place of Publication:Los Alamitos, USA
Date of Publication (YYYY-MM-DD):2008
Title of Proceedings:IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008)
Start Page:1
End Page:8
Place of Conference/Meeting:Anchorage, Alaska
(Start) Date of Conference/Meeting
 (YYYY-MM-DD):
2008-06-24
End Date of Conference/Meeting 
 (YYYY-MM-DD):
2008-06-26
Audience:Experts Only
Intended Educational Use:No
Abstract / Description:We present a dense 3D correspondence finding method
that enables spatio-temporally coherent reconstruction of
surface animations from multi-view video data. Given as input
a sequence of shape-from-silhouette volumes of a moving
subject that were reconstructed for each time frame individually,
our method establishes dense surface correspondences
between subsequent shapes independently of surface
discretization. This is achieved in two steps: first, we obtain
sparse correspondences from robust optical features
between adjacent frames. Second, we generate dense correspondences
which serve as map between respective surfaces.
By applying this procedure subsequently to all pairs
of time steps we can trivially align one shape with all others.
Thus, the original input can be reconstructed as a sequence
of meshes with constant connectivity and small tangential
distortion. We exemplify the performance and accuracy of
our method using several synthetic and captured real-world
sequences.
Last Change of the Resource (YYYY-MM-DD):2009-03-20
External Publication Status:published
Document Type:Conference-Paper
Communicated by:Hans-Peter Seidel
Affiliations:MPI f�r Informatik/Computer Graphics Group
Identifiers:LOCALID:C125756E0038A185-052B4E5D12A0B04EC12574190040B3E5-...
URL:http://dx.doi.org/10.1109/CVPR.2008.4587758
DOI:10.1109/CVPR.2008.4587758
The scope and number of records on eDoc is subject to the collection policies defined by each institute - see "info" button in the collection browse view.