{"day":"01","publication_status":"published","article_processing_charge":"No","page":"65 - 81","doi":"10.1007/3-540-47977-5_5","status":"public","title":"Multi-camera scene reconstruction via graph cuts","publisher":"Springer","publication":"Proceedings of the 7th European Conference on Computer Vision","user_id":"ea97e931-d5af-11eb-85d4-e6957dddbf17","date_updated":"2023-07-18T08:20:02Z","month":"01","date_created":"2018-12-11T12:00:23Z","conference":{"name":"ECCV: European Conference on Computer Vision","location":"Copenhagen, Denmark","start_date":"2002-05-28","end_date":"2002-05-31"},"scopus_import":"1","publication_identifier":{"isbn":["9783540437468"]},"_id":"2927","type":"conference","language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"In the last few years, several new algorithms based on graph cuts have been developed to solve energy minimization problems in computer vision. Each of these techniques constructs a graph such that the minimum cut on the graph also minimizes the energy. Yet because these graph constructions are complex and highly specific to a particular energy function, graph cuts have seen limited application to date. In this paper we characterize the energy functions that can be minimized by graph cuts. Our results are restricted to energy functions with binary variables. However, our work generalizes many previous constructions, and is easily applicable to vision problems that involve large numbers of labels, such as stereo, motion, image restoration and scene reconstruction. We present three main results: a necessary condition for any energy function that can be minimized by graph cuts; a sufficient condition for energy functions that can be written as a sum of functions of up to three variables at a time; and a general-purpose construction to minimize such an energy function. Researchers who are considering the use of graph cuts to optimize a particular energy function can use our results to determine if this is possible, and then follow our construction to create the appropriate graph."}],"author":[{"first_name":"Vladimir","full_name":"Kolmogorov, Vladimir","last_name":"Kolmogorov","id":"3D50B0BA-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Zabih, Ramin","last_name":"Zabih","first_name":"Ramin"}],"publist_id":"3810","citation":{"ieee":"V. Kolmogorov and R. Zabih, “Multi-camera scene reconstruction via graph cuts,” in <i>Proceedings of the 7th European Conference on Computer Vision</i>, Copenhagen, Denmark, 2002, pp. 65–81.","ista":"Kolmogorov V, Zabih R. 2002. Multi-camera scene reconstruction via graph cuts. Proceedings of the 7th European Conference on Computer Vision. ECCV: European Conference on Computer Vision, 65–81.","ama":"Kolmogorov V, Zabih R. Multi-camera scene reconstruction via graph cuts. In: <i>Proceedings of the 7th European Conference on Computer Vision</i>. Springer; 2002:65-81. doi:<a href=\"https://doi.org/10.1007/3-540-47977-5_5\">10.1007/3-540-47977-5_5</a>","mla":"Kolmogorov, Vladimir, and Ramin Zabih. “Multi-Camera Scene Reconstruction via Graph Cuts.” <i>Proceedings of the 7th European Conference on Computer Vision</i>, Springer, 2002, pp. 65–81, doi:<a href=\"https://doi.org/10.1007/3-540-47977-5_5\">10.1007/3-540-47977-5_5</a>.","short":"V. Kolmogorov, R. Zabih, in:, Proceedings of the 7th European Conference on Computer Vision, Springer, 2002, pp. 65–81.","apa":"Kolmogorov, V., &#38; Zabih, R. (2002). Multi-camera scene reconstruction via graph cuts. In <i>Proceedings of the 7th European Conference on Computer Vision</i> (pp. 65–81). Copenhagen, Denmark: Springer. <a href=\"https://doi.org/10.1007/3-540-47977-5_5\">https://doi.org/10.1007/3-540-47977-5_5</a>","chicago":"Kolmogorov, Vladimir, and Ramin Zabih. “Multi-Camera Scene Reconstruction via Graph Cuts.” In <i>Proceedings of the 7th European Conference on Computer Vision</i>, 65–81. Springer, 2002. <a href=\"https://doi.org/10.1007/3-540-47977-5_5\">https://doi.org/10.1007/3-540-47977-5_5</a>."},"oa_version":"None","acknowledgement":"We thank Olga Veksler and Yuri Boykov for their careful reading of this paper, and for valuable comments which greatly improved itsreadibility. We also thank Ian Jermyn for helping us clarify the paper’s motivation. This research was supported by NSF grants IIS-9900115 and CCR-0113371, and by a grant from Microsoft Research.","extern":"1","date_published":"2002-01-01T00:00:00Z","quality_controlled":"1","year":"2002"}