A Renormalization Group Approach to Image Processing Problems
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiscale annealing for grouping and unsupervised texture segmentation
Computer Vision and Image Understanding
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computing Geodesics and Minimal Surfaces via Graph Cuts
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
"GrabCut": interactive foreground extraction using iterated graph cuts
ACM SIGGRAPH 2004 Papers
A Multilevel Banded Graph Cuts Method for Fast Image Segmentation
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Effciently Solving Dynamic Markov Random Fields Using Graph Cuts
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Capturing and viewing gigapixel images
ACM SIGGRAPH 2007 papers
Accurate banded graph cut segmentation of thin structures using laplacian pyramids
MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II
Restriction of a Markov random field on a graph and multiresolution statistical image modeling
IEEE Transactions on Information Theory
SlimCuts: graphcuts for high resolution images using graph reduction
EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
Simultaneous segmentation and filtering via reduced graph cuts
ACIVS'12 Proceedings of the 14th international conference on Advanced Concepts for Intelligent Vision Systems
Efficient pixel-grouping based on dempster's theory of evidence for image segmentation
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Hi-index | 0.00 |
This paper proposes a new multi-scale energy minimization algorithm which can be used to efficiently solve large scale labelling problems in computer vision. The basic modus operandi of any multi-scale method involves the construction of a smaller problem which can be solved efficiently. The solution of this problem is used to obtain a partial labelling of the original energy function, which in turn allows us to minimize it by solving its (much smaller) projection. We propose the use of new techniques for both the construction of the smaller problem, and the extraction of a partial solution. Experiments on image segmentation show that our techniques give solutions with low pixel labelling error and in the same or less amount of computation time, compared to traditional multi-scale techniques.