Campus Event Calendar
Event Entry
What and Who
From Image-based Motion Analysis To Free-Viewpoint Video
Christian Theobalt
Max-Planck-Institut für Informatik - AG 4
Promotionskolloquium
AG 1, AG 2, AG 3, AG 4, AG 5
Expert Audience
Note: We use this to send email in the morning.
Date, Time and Location
Tuesday, 27 December 2005
10:00
-- Not specified --
E1.4 - MPII
024
Saarbrücken
Abstract
The questions of how to capture real-world scenes with imaging devices
and how to automatically analyze the visible motion have traditionally
been in the focus of computer vision research.
The photo-realistic rendition of dynamic real-world scenes, on the other
hand, is a problem traditionally researched in
the field of computer graphics. In this talk, it will be demonstrated that
the joint solution to all three of these problems paves the trail for
interesting novel ways of analyzing and visualizing human motion.
In part one, new solutions to two important
problems in video-based human motion analysis, marker-less motion capture
and marker-less body model estimation, are briefly outlined.
Part two illustrates how a marker-free motion capture approach makes
possible the model-based reconstruction of free-viewpoint videos of
human actors from only a handful of video
streams. The estimated 3D videos enable the photo-realistic real-time
rendition of a dynamic scene from arbitrary novel viewpoints and
under novel virtual lighting conditions.
A new method to capture and visualize high-speed motion using regular
photo cameras and the principle of multi-exposure photography is
described in part three.
and how to automatically analyze the visible motion have traditionally
been in the focus of computer vision research.
The photo-realistic rendition of dynamic real-world scenes, on the other
hand, is a problem traditionally researched in
the field of computer graphics. In this talk, it will be demonstrated that
the joint solution to all three of these problems paves the trail for
interesting novel ways of analyzing and visualizing human motion.
In part one, new solutions to two important
problems in video-based human motion analysis, marker-less motion capture
and marker-less body model estimation, are briefly outlined.
Part two illustrates how a marker-free motion capture approach makes
possible the model-based reconstruction of free-viewpoint videos of
human actors from only a handful of video
streams. The estimated 3D videos enable the photo-realistic real-time
rendition of a dynamic scene from arbitrary novel viewpoints and
under novel virtual lighting conditions.
A new method to capture and visualize high-speed motion using regular
photo cameras and the principle of multi-exposure photography is
described in part three.
Contact
Christian Theobalt
419
--email hidden
passcode not visible
logged in users only
Sabine Budde, 12/19/2005 09:58 -- Created document.