Authors:
Andrea Bönsch
1
;
Andrew Feng
2
;
Parth Patel
2
and
Ari Shapiro
2
Affiliations:
1
Visual Computing Institute, RWTH Aachen University, Aachen and Germany
;
2
Institute for Creative Technologies, University of Southern California, Los Angeles and U.S.A.
Keyword(s):
Avatar, Video Capture, Photogrammetry, Low-cost, Animation.
Related
Ontology
Subjects/Areas/Topics:
Animation and Simulation
;
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Geometry and Modeling
;
Human Figure Animation
;
Image-Based Animation
;
Image-Based Modeling
;
Pattern Recognition
;
Software Engineering
;
Surface Modeling
Abstract:
Volumetric video can be used in virtual and augmented reality applications to show detailed animated performances by human actors. In this paper, we describe a volumetric capture system based on a photogrammetry cage with unsynchronized, low-cost cameras which is able to generate high-quality geometric data for animated avatars. This approach requires, inter alia, a subsequent synchronization of the captured videos.