Share Email Print

Proceedings Paper

Encoding scene structures for video compression
Author(s): Georgios Georgiadis; Avinash Ravichandran; Stefano Soatto; Alessandro Chiuso
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We describe an approach to partition a video stream into structure regions that are temporally encoded and disjoint from texture regions that are synthesized so as to preserve the statistical properties of the original data stream. Structures encode regions of an image that can be put into correspondence in different images of the same scene, and are encoded via a dictionary that takes into account spatial and temporal regularities. Textures are synthesized in a manner that preserves perceptual similarity.

Paper Details

Date Published: 15 October 2012
PDF: 9 pages
Proc. SPIE 8499, Applications of Digital Image Processing XXXV, 84991G (15 October 2012); doi: 10.1117/12.930318
Show Author Affiliations
Georgios Georgiadis, Univ. of California, Los Angeles (United States)
Avinash Ravichandran, Univ. of California, Los Angeles (United States)
Stefano Soatto, Univ. of California, Los Angeles (United States)
Alessandro Chiuso, Univ. degli Studi di Padova (Italy)

Published in SPIE Proceedings Vol. 8499:
Applications of Digital Image Processing XXXV
Andrew G. Tescher, 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?