Abstract
We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. The approach extends traditional Markov random field (MRF) models by learning potential functions over extended pixel neighborhoods. Field potentials are modeled using a Products-of-Experts framework that exploits nonlinear functions of many linear filter responses. In contrast to previous MRF approaches all parameters, including the linear filters themselves, are learned from training data. We demonstrate the capabilities of this Field of Experts model with two example applications, image denoising and image inpainting, which are implemented using a simple, approximate inference scheme. While the model is trained on a generic image database and is not tuned toward a specific application, we obtain results that compete with and even outperform specialized techniques.
Keywords
InpaintingMarkov random fieldPrior probabilityComputer scienceArtificial intelligenceInferenceImage editingField (mathematics)Image (mathematics)Machine learningPixelMarkov chainComputer visionFilter (signal processing)Pattern recognition (psychology)MathematicsImage segmentation
Affiliated Institutions
Related Publications
From learning models of natural image patches to whole image restoration
Learning good image priors is of utmost importance for the study of vision, computer vision and image processing applications. Learning priors and optimizing over whole images c...
The mean field theory in EM procedures for blind Markov random field image restoration
A Markov random field (MRF) model-based EM (expectation-maximization) procedure for simultaneously estimating the degradation model and restoring the image is described. The MRF...
Texture synthesis by non-parametric sampling
A non-parametric method for texture synthesis is proposed. The texture synthesis process grows a new image outward from an initial seed, one pixel at a time. A Markov random fie...
Unsupervised image segmentation
We present an unsupervised segmentation algorithm comprising an annealing process to select the maximum a posteriori (MAP) realization of a hierarchical Markov random field (MRF...
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D image...
Publication Info
- Year
- 2005
- Type
- article
- Volume
- 2
- Pages
- 860-867
- Citations
- 1053
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1053
OpenAlex
Cite This
Stefan Roth,
M.J. Black
(2005).
Fields of Experts: A Framework for Learning Image Priors.
, 2
, 860-867.
https://doi.org/10.1109/cvpr.2005.160
Identifiers
- DOI
- 10.1109/cvpr.2005.160