Steerable random fields for image restoration and inpainting


Book Chapter


This chapter introduces the concept of a Steerable Random Field (SRF). In contrast to traditional Markov random field (MRF) models in low-level vision, the random field potentials of a SRF are defined in terms of filter responses that are steered to the local image structure. This steering uses the structure tensor to obtain derivative responses that are either aligned with, or orthogonal to, the predominant local image structure. Analysis of the statistics of these steered filter responses in natural images leads to the model proposed here. Clique potentials are defined over steered filter responses using a Gaussian scale mixture model and are learned from training data. The SRF model connects random fields with anisotropic regularization and provides a statistical motivation for the latter. Steering the random field to the local image structure improves image denoising and inpainting performance compared with traditional pairwise MRFs.

Author(s): Roth, S. and Black, M. J.
Book Title: Markov Random Fields for Vision and Image Processing
Pages: 377--387
Year: 2011
Editors: Blake, A. and Kohli, P. and Rother, C.
Publisher: MIT Press

Department(s): Perceiving Systems
Research Project(s): High-level Priors
Bibtex Type: Book Chapter (incollection)
Paper Type: Book Chapter

Links: publisher site


  title = {Steerable random fields for image restoration and inpainting},
  author = {Roth, S. and Black, M. J.},
  booktitle = {Markov Random Fields for Vision and Image Processing},
  pages = {377--387},
  editors = {Blake, A. and Kohli, P. and Rother, C.},
  publisher = {MIT Press},
  year = {2011}