By Topic

Large scene reconstruction with local details recovery

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
S. H. Or ; Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, China ; K. H. Wong ; M. M. Y. Chang ; C. Y. Ip

We propose a method to recover the global structure with local details around a point. To handle a large scale of motion i.e. 360 degree around the point, we use an optimization-based algorithm to estimate the structure from the panorama around the fixed camera point. The global structure estimated can thus be used to initialize a structure from motion algorithm to recover the local details through simple camera motion such as panning. Synthetic as well as real data are used to test the validity of the algorithm. Our method can be used in applications such as authoring of virtual environments from a real scene.

Published in:

Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on  (Volume:4 )

Date of Conference:

23-26 Aug. 2004