Non-parametric CRFs for Image Labeling

We introduce a powerful non-parametric image labeling framework, Regression Tree Fields (RTFs), and discuss its application to image restoration. The conditional structure and the parameters of our model are estimated from training data so as to directly optimize for popular performance measures, resulting in excellent predictive performance at low computational cost.

[1]  F. Downton,et al.  Introduction to Mathematical Statistics , 1959 .

[2]  Sebastian Nowozin,et al.  Regression Tree Fields — An efficient, non-parametric approach to image labeling problems , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Sebastian Nowozin,et al.  Loss-Specific Training of Non-Parametric Image Restoration Models: A New State of the Art , 2012, ECCV.

[4]  Pushmeet Kohli,et al.  Markov Random Fields for Vision and Image Processing , 2011 .

[5]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[6]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Edward H. Adelson,et al.  Learning Gaussian Conditional Random Fields for Low-Level Vision , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[9]  Yair Weiss,et al.  From learning models of natural image patches to whole image restoration , 2011, 2011 International Conference on Computer Vision.

[10]  J. Besag.  Efficiency of pseudolikelihood estimation for simple Gaussian fields , 1977 .

[11]  Qi Gao,et al.  A generative perspective on MRFs in low-level vision , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Guillermo Sapiro,et al.  Non-local sparse models for image restoration , 2009, 2009 IEEE 12th International Conference on Computer Vision.