Inducing Features of Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Pixel Dissimilarity Measure That Is Insensitive to Image Sampling
IEEE Transactions on Pattern Analysis and Machine Intelligence
A revolution: belief propagation in graphs with cycles
NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
An Introduction to Variational Methods for Graphical Models
Machine Learning
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Probabilistic Networks and Expert Systems
Probabilistic Networks and Expert Systems
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
International Journal of Computer Vision
Stereo Matching with Segmentation-Based Cooperation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
What Energy Functions Can Be Minimized via Graph Cuts?
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Multi-camera Scene Reconstruction via Graph Cuts
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Understanding belief propagation and its generalizations
Exploring artificial intelligence in the new millennium
Stereo Matching Using Belief Propagation
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Journal of Machine Learning Research
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
Dense Matching of Multiple Wide-baseline Views
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
ICML '04 Proceedings of the twenty-first international conference on Machine learning
High-quality video view interpolation using a layered representation
ACM SIGGRAPH 2004 Papers
Parameter Estimation for MRF Stereo
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Symmetric Stereo Matching for Occlusion Handling
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
A Comparison of Algorithms for Inference and Learning in Probabilistic Graphical Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Journal of Machine Learning Research
International Journal of Computer Vision
Efficient Belief Propagation for Early Vision
International Journal of Computer Vision
Accelerated training of conditional random fields with stochastic gradient methods
ICML '06 Proceedings of the 23rd international conference on Machine learning
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Probabilistic Fusion of Stereo with Color and Contrast for Bilayer Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Convergent Tree-Reweighted Message Passing for Energy Minimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
An asymptotic analysis of generative, discriminative, and pseudolikelihood estimators
Proceedings of the 25th international conference on Machine learning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficiently Learning Random Fields for Stereo Vision with Sparse Message Passing
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Scene Text Recognition Using Similarity and a Lexicon with Sparse Belief Propagation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiscale conditional random fields for image labeling
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
High-accuracy stereo depth maps using structured light
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Loopy belief propagation for approximate inference: an empirical study
UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Factor graphs and the sum-product algorithm
IEEE Transactions on Information Theory
Tree-based reparameterization framework for analysis of sum-product and related algorithms
IEEE Transactions on Information Theory
MAP estimation via agreement on trees: message-passing and linear programming
IEEE Transactions on Information Theory
Guest Editorial: Special Issue on Structured Prediction and Inference
International Journal of Computer Vision
Guided depth enhancement via a fast marching method
Image and Vision Computing
Hi-index | 0.00 |
Until recently, the lack of ground truth data has hindered the application of discriminative structured prediction techniques to the stereo problem. In this paper we use ground truth data sets that we have recently constructed to explore different model structures and parameter learning techniques. To estimate parameters in Markov random fields (MRFs) via maximum likelihood one usually needs to perform approximate probabilistic inference. Conditional random fields (CRFs) are discriminative versions of traditional MRFs. We explore a number of novel CRF model structures including a CRF for stereo matching with an explicit occlusion model. CRFs require expensive inference steps for each iteration of optimization and inference is particularly slow when there are many discrete states. We explore belief propagation, variational message passing and graph cuts as inference methods during learning and compare with learning via pseudolikelihood. To accelerate approximate inference we have developed a new method called sparse variational message passing which can reduce inference time by an order of magnitude with negligible loss in quality. Learning using sparse variational message passing improves upon previous approaches using graph cuts and allows efficient learning over large data sets when energy functions violate the constraints imposed by graph cuts.