Texture synthesis via a noncausal nonparametric multiscale Markov random field

  • Authors:
  • R. Paget;I. D. Longstaff

  • Affiliations:
  • Dept. of Electr. & Comput. Eng., Queensland Univ., Brisbane, Qld.;-

  • Venue:
  • IEEE Transactions on Image Processing
  • Year:
  • 1998

Quantified Score

Hi-index 0.01

Visualization

Abstract

Our noncausal, nonparametric, multiscale, Markov random field (MRF) model is capable of synthesizing and capturing the characteristics of a wide variety of textures, from the highly structured to the stochastic. We use a multiscale synthesis algorithm incorporating local annealing to obtain larger realizations of texture visually indistinguishable from the training texture