Share Email Print

Proceedings Paper

Video inpainting algorithm using spatio-temporal consistency
Author(s): Sang-Heon Lee; Soon-Young Lee; Jun-Hee Heu; Chang-Su Kim; Sang-Uk Lee
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A new video inpainting algorithm is proposed for removing unwanted or erroneous objects from video data. The proposed algorithm fills a mask region with source blocks from unmasked areas, while keeping spatio-temporal consistency. First, a 3-dimensional graph is constructed over consecutive frames. It defines a structure of nodes over which the source blocks are pasted. Then, we form temporal block bundles using the motion information. The best block bundles, which minimize an objective function, are arranged in the 3-dimensional graph. Extensive simulation results demonstrate that the proposed algorithm can yield visually pleasing video inpainting results even for dynamic sequences.

Paper Details

Date Published: 2 February 2009
PDF: 8 pages
Proc. SPIE 7246, Computational Imaging VII, 72460N (2 February 2009); doi: 10.1117/12.805892
Show Author Affiliations
Sang-Heon Lee, Seoul National Univ. (Korea, Republic of)
Soon-Young Lee, Seoul National Univ. (Korea, Republic of)
Jun-Hee Heu, Seoul National Univ. (Korea, Republic of)
Chang-Su Kim, Korea Univ. (Korea, Republic of)
Sang-Uk Lee, Seoul National Univ. (Korea, Republic of)

Published in SPIE Proceedings Vol. 7246:
Computational Imaging VII
Charles A. Bouman; Eric L. Miller; Ilya Pollak, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?