Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image Segmentation by Data-Driven Markov Chain Monte Carlo
IEEE Transactions on Pattern Analysis and Machine Intelligence
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Learning from Labeled and Unlabeled Data using Graph Mincuts
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
What Energy Functions Can Be Minimizedvia Graph Cuts?
IEEE Transactions on Pattern Analysis and Machine Intelligence
"GrabCut": interactive foreground extraction using iterated graph cuts
ACM SIGGRAPH 2004 Papers
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision
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
Random Walks for Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Star Shape Prior for Graph-Cut Image Segmentation
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Cosegmentation revisited: models and optimization
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Spatially coherent clustering using graph cuts
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Inducing semantic segmentation from an example
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
Fast Approximate Energy Minimization with Label Costs
International Journal of Computer Vision
Energy-Based Geometric Multi-model Fitting
International Journal of Computer Vision
Minimizing Energies with Hierarchical Costs
International Journal of Computer Vision
Annotation propagation in large image databases via dense image correspondence
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Interactive segmentation with recommendation of most informative regions
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Efficient 3D multi-region prostate MRI segmentation using dual optimization
IPMI'13 Proceedings of the 23rd international conference on Information Processing in Medical Imaging
Hi-index | 0.00 |
In interactive segmentation, the most common way to model object appearance is by GMM or histogram, while MRFs are used to encourage spatial coherence among the object labels. This makes the strong assumption that pixels within each object are i.i.d. when in fact most objects have multiple distinct appearances and exhibit strong spatial correlation among their pixels. At the very least, this calls for an MRF-based appearance model within each object itself and yet, to the best of our knowledge, such a "two-level MRF" has never been proposed. We propose a novel segmentation energy that can model complex appearance. We represent the appearance of each object by a set of distinct spatially coherent models. This results in a two-level MRF with "superlabels" at the top level that are partitioned into "sub-labels" at the bottom. We introduce the hierarchical Potts (hPotts) prior to govern spatial coherence within each level. Finally, we introduce a novel algorithm with EM-style alternation of proposal, a-expansion and re-estimation steps. Our experiments demonstrate the conceptual and qualitative improvement that a two-level MRF can provide. We show applications in binary segmentation, multi-class segmentation, and interactive co-segmentation. Finally, our energy and algorithm have interesting interpretations in terms of semi-supervised learning.