Modeling dynamic scenes with active appearance

Doretto, G. and Soatto, S.
Modeling dynamic scenes with active appearance. Technical Report TR040053, UCLA Computer Science Department, 2004.

Download

PDF (265.6kB )  

Abstract

In this work we propose a model for video scenes that contain temporal variability in shape and appearance. We propose a conditionally linear model akin to a dynamic extension of active appearance models. We formulate the problem variationally, and use finite-element methods to compute a numerical solution. We illustrate our model to learn and simulate the shape, appearance, and motion of scenes that exhibit some form of temporal regularity, intended in a statistical sense.

@TECHREPORT{UCLA-CSD-TR040053,
  author = {Doretto, G. and Soatto, S.},
  title = {Modeling dynamic scenes with active appearance},
  institution = {UCLA Computer Science Department},
  year = {2004},
  number = {TR040053},
  address = {Los Angeles, CA, USA},
  month = dec,
  bib2html_pubtype = {Tech Reports},
  bib2html_rescat = {Dynamic Textures, Shape and Appearance Modeling, Visual Motion Analysis,
	Image Based Rendering},
  abstract = {In this work we propose a model for video scenes that contain temporal
	variability in shape and appearance. We propose a conditionally linear
	model akin to a dynamic extension of active appearance models. We
	formulate the problem variationally, and use finite-element methods
	to compute a numerical solution. We illustrate our model to learn
	and simulate the shape, appearance, and motion of scenes that exhibit
	some form of temporal regularity, intended in a statistical sense.},
  file = {UCLA-CSD-TR040053.pdf:doretto\\report\\UCLA-CSD-TR040053.pdf:PDF},
  owner = {doretto},
  pdf = {doretto\report\UCLA-CSD-TR040053.pdf}
}

Generated by bib2html.pl (written by Patrick Riley )