Texture synthesis via a noncausal nonparametric multiscale Markov random field

Abstract— Our noncausal, nonparametric, multiscale, Markov random field (MRF) model is capable of synthesising 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 realisations of texture visually indistinguishable from the training texture. Keywords— Markov random fields, Nonparametric estimation, Texture synthesis, Multi-resolution, Local annealing.

• Type: Journal
• Year: 1998
• Where: TIP
• Authors: Rupert Paget, I. Dennis Longstaff
• Keywords: Keywords— Markov Random, Markov Random, Multiscale Synthesis Algorithm, TIP 1998