Paper
28 January 2008 Stochastic texture synthesis for video compression
Author Affiliations +
Proceedings Volume 6822, Visual Communications and Image Processing 2008; 68220X (2008) https://doi.org/10.1117/12.765368
Event: Electronic Imaging, 2008, San Jose, California, United States
Abstract
Low-bitrate digital video often suffers from the artifact of texture flattening. Texture synthesis can be used to revive the removed texture. Patch-based synthesis provides a quite general method for texture synthesis. However, this method still requires a substantial bitrate to transmit example patches. We propose a method for stochastic texture synthesis which requires only a very low bitrate (less than 1 kbit/sec) that can replace patch-based synthesis for random textures. Spatial correlation is modeled as a 2-dimensional Moving Average (MA) process. To achieve a faithful representation of temporal evolution, we use a translation+scaling motion model combined with a finite impulse response (FIR) filter. Experiments show that we can successfully reduce texture flattening for a range of random textures such as grass and roads.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Stijn de Waele and Fei Zuo "Stochastic texture synthesis for video compression", Proc. SPIE 6822, Visual Communications and Image Processing 2008, 68220X (28 January 2008); https://doi.org/10.1117/12.765368
Lens.org Logo
CITATIONS
Cited by 2 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Motion models

Autoregressive models

Video

Video compression

Platinum

Stochastic processes

Optical filters

Back to Top