Representing moving images with layers
Authors:
- J.Y.A. WangJWJ.Y.A. Wang
- E.H. AdelsonEAE.H. Adelson
- 1 January 1994
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 3 (5) , 625-638
Abstract
We describe a system for representing moving images with sets of overlapping layers. Each layer contains an intensity map that defines the additive values of each pixel, along with an alpha map that serves as a mask indicating the transparency. The layers are ordered in depth and they occlude each other in accord with the rules of compositing. Velocity maps define how the layers are to be warped over time. The layered representation is more flexible than standard image transforms and can capture many important properties of natural image sequences. We describe some methods for decomposing image sequences into layers using motion analysis, and we discuss how the representation may be used for image coding and other applications.Keywords
This publication has 6 references indexed in Scilit:
- Analysis and synthesis of facial image sequences using physical and anatomical modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
- Adaptive transform image coding based on variable-shape block segmentation with smoothing filter1992
- Iterative motion estimation method using triangular patches for motion compensation1991
- Human facial motion modeling, analysis, and synthesis for video compression1991
- Motion compensation for video compression using control grid interpolation1991
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988