Partial Enumeration and Curvature Regularization
Författare
Summary, in English
Energies with high-order non-submodular interactions have been shown to be very useful in vision due to their high modeling power. Optimization of such energies, however, is generally NP-hard. A naive approach that works for small problem instances is exhaustive search, that is, enumera- tion of all possible labelings of the underlying graph. We propose a general minimization approach for large graphs based on enumeration of labelings of certain small patches. This partial enumeration technique reduces complex high- order energy formulations to pairwise Constraint Satisfac- tion Problems with unary costs (uCSP), which can be ef- ficiently solved using standard methods like TRW-S. Our approach outperforms a number of existing state-of-the-art algorithms on well known difficult problems (e.g. curvature regularization, stereo, deconvolution); it gives near global minimum and better speed. Our main application of interest is curvature regular- ization. In the context of segmentation, our partial enu- meration technique allows to evaluate curvature directly on small patches using a novel integral geometry approach.
Avdelning/ar
Publiceringsår
2013
Språk
Engelska
Sidor
2936-2943
Publikation/Tidskrift/Serie
Computer Vision (ICCV), 2013 IEEE International Conference on
Fulltext
- Available as PDF - 530 kB
- Download statistics
Dokumenttyp
Konferensbidrag
Förlag
IEEE - Institute of Electrical and Electronics Engineers Inc.
Ämne
- Mathematics
- Computer Vision and Robotics (Autonomous Systems)
Conference name
IEEE International Conference on Computer Vision (ICCV), 2013
Conference date
2013-12-01 - 2013-12-08
Conference place
Sydney, Australia
Status
Published
Forskningsgrupp
- Mathematical Imaging Group
ISBN/ISSN/Övrigt
- ISSN: 1550-5499