Applications of parametric maxflow in computer vision Export

@inproceedings{citeulike:3766998, abstract = {The maximum flow algorithm for minimizing energy functions of binary variables has become a standard tool in computer vision. In many cases, unary costs of the energy depend linearly on parameter lambda. In this paper we study vision applications for which it is important to solve the maxflow problem for different lambda's. An example is a weighting between data and regularization terms in image segmentation or stereo: it is desirable to vary it both during training (to learn lambda from ground truth data) and testing (to select best lambda using high-knowledge constraints, e.g. user input). We review algorithmic aspects of this parametric maximum flow problem previously unknown in vision, such as the ability to compute all breakpoints of lambda and corresponding optimal configurations infinite time. These results allow, in particular, to minimize the ratio of some geometric functional, such as flux of a vector field over length (or area). Previously, such functional were tackled with shortest path techniques applicable only in 2D. We give theoretical improvements for "PDE cuts" [5]. We present experimental results for image segmentation, 3D reconstruction, and the cosegmentation problem.}, author = {Kolmogorov, V. and Boykov, Y. and Rother, C.}, booktitle = {Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on}, citeulike-article-id = {3766998}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/ICCV.2007.4408910}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4408910}, doi = {10.1109/ICCV.2007.4408910}, journal = {Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on}, keywords = {maxflow, mincut, segmentation, vision}, pages = {1--8}, posted-at = {2009-03-18 17:56:21}, priority = {2}, title = {Applications of parametric maxflow in computer vision}, url = {http://dx.doi.org/10.1109/ICCV.2007.4408910}, year = {2007} }

TY - CONF ID - citeulike:3766998 L3 - citeulike-article-id:3766998 N2 - The maximum flow algorithm for minimizing energy functions of binary variables has become a standard tool in computer vision. In many cases, unary costs of the energy depend linearly on parameter lambda. In this paper we study vision applications for which it is important to solve the maxflow problem for different lambda's. An example is a weighting between data and regularization terms in image segmentation or stereo: it is desirable to vary it both during training (to learn lambda from ground truth data) and testing (to select best lambda using high-knowledge constraints, e.g. user input). We review algorithmic aspects of this parametric maximum flow problem previously unknown in vision, such as the ability to compute all breakpoints of lambda and corresponding optimal configurations infinite time. These results allow, in particular, to minimize the ratio of some geometric functional, such as flux of a vector field over length (or area). Previously, such functional were tackled with shortest path techniques applicable only in 2D. We give theoretical improvements for "PDE cuts" [5]. We present experimental results for image segmentation, 3D reconstruction, and the cosegmentation problem. JF - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on EP - 8 TI - Applications of parametric maxflow in computer vision T2 - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on SP - 1 KW - maxflow KW - mincut KW - segmentation KW - vision AU - Kolmogorov, V AU - Boykov, Y AU - Rother, C PY - 2007/// UR - http://dx.doi.org/10.1109/ICCV.2007.4408910 ER -