Training an active random field for real-time image denoising

Authors:
Adrian Barbu
Affiliations:
Department of Statistics, Florida State University, Tallahassee, FL
Venue:
IEEE Transactions on Image Processing
Year:
2009

Citing 25
Cited 2

On the limited memory BFGS method for large scale optimization

Mathematical Programming: Series A and B
Filters, Random Fields and Maximum Entropy (FRAME): Towards a Unified Theory for Texture Modeling

International Journal of Computer Vision
Learning Low-Level Vision

International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
Active Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Training products of experts by minimizing contrastive divergence

Neural Computation
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
A Review of Nonlinear Diffusion Filtering

SCALE-SPACE '97 Proceedings of the First International Conference on Scale-Space Theory in Computer Vision
Stereo Matching Using Belief Propagation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Comparison of Graph Cuts with Belief Propagation for Stereo, using Identical MRF Parameters

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
A Non-Local Algorithm for Image Denoising

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Globally Optimal Solutions for Energy Minimization in Stereo Vision Using Reweighted Belief Propagation

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Estimating the "Wrong" Graphical Model: Benefits in the Computation-Limited Setting

The Journal of Machine Learning Research
Fields of Experts

International Journal of Computer Vision
SATzilla: portfolio-based algorithm selection for SAT

Journal of Artificial Intelligence Research
Cost-sensitive classification: empirical evaluation of a hybrid genetic decision tree induction algorithm

Journal of Artificial Intelligence Research
Shape regression machine

IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
Image denoising using scale mixtures of Gaussians in the wavelet domain

IEEE Transactions on Image Processing
Image quality assessment: from error visibility to structural similarity

IEEE Transactions on Image Processing
Toward automatic phenotyping of developing embryos from videos

IEEE Transactions on Image Processing
Estimating the probability of the presence of a signal of interest in multiresolution single- and multiband image denoising

IEEE Transactions on Image Processing
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries

IEEE Transactions on Image Processing
Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering

IEEE Transactions on Image Processing

Stacked hierarchical labeling

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Training energy-based models for time-series imputation

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.01

Visualization

Abstract

Many computer vision problems can be formulated in a Bayesian framework based on Markov random fields (MRF) or conditional random fields (CRF). Generally, the MRF/CRF model is learned independently of the inference algorithm that is used to obtain the final result. In this paper, we observe considerable gains in speed and accuracy by training the MRF/CRF model together with a fast and suboptimal inference algorithm. An active random field (ARF) is defined as a combination of a MRF/CRF based model and a fast inference algorithm for the MRF/CRF model. This combination is trained through an optimization of a loss function and a training set consisting of pairs of input images and desired outputs. We apply the ARF concept to image denoising, using the Fields of Experts MRF together with a 1-4 iteration gradient descent algorithm for inference. Experimental validation on unseen data shows that the ARF approach obtains an improved benchmark performance as well as a 1000-3000 times speedup compared to the Fields of Experts MRF. Using the ARF approach, image denoising can be performed in real-time, at 8fps on a single CPU for a 256 × 256 image sequence, with close to state-of-the-art accuracy.