{"publisher":"IEEE","status":"public","year":"2007","day":"26","date_published":"2007-12-26T00:00:00Z","citation":{"chicago":"Kolmogorov, Vladimir, Yuri Boykov, and Carsten Rother. “Applications of Parametric Maxflow in Computer Vision.” IEEE, 2007. <a href=\"https://doi.org/10.1109/ICCV.2007.4408910\">https://doi.org/10.1109/ICCV.2007.4408910</a>.","ista":"Kolmogorov V, Boykov Y, Rother C. 2007. Applications of parametric maxflow in computer vision. ICCV: International Conference on Computer Vision.","apa":"Kolmogorov, V., Boykov, Y., &#38; Rother, C. (2007). Applications of parametric maxflow in computer vision. Presented at the ICCV: International Conference on Computer Vision, IEEE. <a href=\"https://doi.org/10.1109/ICCV.2007.4408910\">https://doi.org/10.1109/ICCV.2007.4408910</a>","mla":"Kolmogorov, Vladimir, et al. <i>Applications of Parametric Maxflow in Computer Vision</i>. IEEE, 2007, doi:<a href=\"https://doi.org/10.1109/ICCV.2007.4408910\">10.1109/ICCV.2007.4408910</a>.","ama":"Kolmogorov V, Boykov Y, Rother C. Applications of parametric maxflow in computer vision. In: IEEE; 2007. doi:<a href=\"https://doi.org/10.1109/ICCV.2007.4408910\">10.1109/ICCV.2007.4408910</a>","short":"V. Kolmogorov, Y. Boykov, C. Rother, in:, IEEE, 2007.","ieee":"V. Kolmogorov, Y. Boykov, and C. Rother, “Applications of parametric maxflow in computer vision,” presented at the ICCV: International Conference on Computer Vision, 2007."},"month":"12","date_created":"2018-12-11T12:01:55Z","_id":"3191","main_file_link":[{"open_access":"0","url":"http://research.microsoft.com/pubs/70474/iccv07-paramaxflow.pdf"}],"conference":{"name":"ICCV: International Conference on Computer Vision"},"doi":"10.1109/ICCV.2007.4408910","author":[{"full_name":"Vladimir Kolmogorov","first_name":"Vladimir","last_name":"Kolmogorov","id":"3D50B0BA-F248-11E8-B48F-1D18A9856A87"},{"last_name":"Boykov","first_name":"Yuri","full_name":"Boykov, Yuri"},{"last_name":"Rother","first_name":"Carsten","full_name":"Rother, Carsten"}],"quality_controlled":0,"title":"Applications of parametric maxflow in computer vision","publication_status":"published","abstract":[{"lang":"eng","text":"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 &quot;PDE cuts&quot; [5]. We present experimental results for image segmentation, 3D reconstruction, and the cosegmentation problem."}],"date_updated":"2021-01-12T07:41:41Z","publist_id":"3489","extern":1,"type":"conference"}