Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
International Journal of Computer Vision
Occlusions, Discontinuities, and Epipolar Lines in Stereo
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
What Energy Functions Can Be Minimized via Graph Cuts?
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Multi-camera Scene Reconstruction via Graph Cuts
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Markov Random Fields with Efficient Approximations
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Graphcut textures: image and video synthesis using graph cuts
ACM SIGGRAPH 2003 Papers
Interactive digital photomontage
ACM SIGGRAPH 2004 Papers
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Motion Layer Extraction in the Presence of Occlusion Using Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
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
IEEE Transactions on Pattern Analysis and Machine Intelligence
Global optimization for first order Markov random fields with submodular priors
IWCIA'08 Proceedings of the 12th international conference on Combinatorial image analysis
CVPR'03 Proceedings of the 2003 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
Oriented visibility for multiview reconstruction
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Comparison of energy minimization algorithms for highly connected graphs
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Exact optimization for Markov random fields with convex priors
IEEE Transactions on Pattern Analysis and Machine Intelligence
A fast solver for truncated-convex priors: quantized-convex split moves
EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
Multi-label Moves for MRFs with Truncated Convex Priors
International Journal of Computer Vision
Review article: Multilabel partition moves for MRF optimization
Image and Vision Computing
Hi-index | 0.00 |
Optimization with graph cuts became very popular in recent years. As more applications rely on graph cuts, different energy functions are being employed. Recent evaluation of optimization algorithms showed that the widely used swap and expansion graph cut algorithms have an excellent performance for energies where the underlying MRF has Potts prior. Potts prior corresponds to assuming that the true labeling is piecewise constant. While surprisingly useful in practice, Potts prior is clearly not appropriate in many circumstances. However for more general priors, the swap and expansion algorithms do not perform as well. Both algorithms are based on moves that give each pixel a choice of only two labels. Therefore such moves can be referred to as binary moves. Recently, range moves that act on multiple labels simultaneously were introduced. As opposed to swap and expansion, each pixel has a choice of more than two labels in a range move. Therefore we call them multi-label moves. Range moves were shown to work better for problems with truncated convex priors, which imply a piecewise smooth labeling. Inspired by range moves, we develop several different variants of multi-label moves. We evaluate them on the problem of stereo correspondence and discuss their relative merits.