Campus Event Calendar
Event Entry
New for: D3
What and Who
Recovering Geometric Information by Detecting Symmetries in Images
Justin Parks
International Max Planck Research School for Computer Science - IMPRS
Talk
AG 1, AG 3, AG 4, AG 5, SWS, RG1, MMCI
Public Audience
English
Note: We use this to send email in the morning.
Date, Time and Location
Thursday, 26 November 2009
17:00
60 Minutes
E1 4
024
Saarbrücken
Abstract
While not guaranteed to be present in any given scene, the appearance of
symmetric, geometric structures in an image is one of the most powerful
sources of spatial information to be found. Scenes of man-made structures
can easily yield sufficient symmetry to greatly assist in the
reconstruction of the scene. We consider here a couple of methods for
extracting unknown 2D symmetry classes from raw images, particularly the
graph-based approach. Thus identifying one or more symmetry classes in one
or more images facilitates a multitude of applications ranging from
automatic image and geometry segmentation to geometric noise reduction and
occlusion removal to geometric scene reconstruction from images and pose
recovery.
symmetric, geometric structures in an image is one of the most powerful
sources of spatial information to be found. Scenes of man-made structures
can easily yield sufficient symmetry to greatly assist in the
reconstruction of the scene. We consider here a couple of methods for
extracting unknown 2D symmetry classes from raw images, particularly the
graph-based approach. Thus identifying one or more symmetry classes in one
or more images facilitates a multitude of applications ranging from
automatic image and geometry segmentation to geometric noise reduction and
occlusion removal to geometric scene reconstruction from images and pose
recovery.
Contact
imprs
225
--email hidden
passcode not visible
logged in users only
Jennifer Gerling, 11/25/2009 09:42 -- Created document.