{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cbmv-a-coalesced-bidirectional-matching","title":"CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation","arxiv_id":"1804.01967","date":"2018-04-05","proceeding":"CVPR 2018 6","authors":["Konstantinos Batsos","Changjiang Cai","Philippos Mordohai"],"abstract":"Recently, there has been a paradigm shift in stereo matching with\nlearning-based methods achieving the best results on all popular benchmarks.\nThe success of these methods is due to the availability of training data with\nground truth; training learning-based systems on these datasets has allowed\nthem to surpass the accuracy of conventional approaches based on heuristics and\nassumptions. Many of these assumptions, however, had been validated extensively\nand hold for the majority of possible inputs. In this paper, we generate a\nmatching volume leveraging both data with ground truth and conventional wisdom.\nWe accomplish this by coalescing diverse evidence from a bidirectional matching\nprocess via random forest classifiers. We show that the resulting matching\nvolume estimation method achieves similar accuracy to purely data-driven\nalternatives on benchmarks and that it generalizes to unseen data much better.\nIn fact, the results we submitted to the KITTI and ETH3D benchmarks were\ngenerated using a classifier trained on the Middlebury 2014 dataset.","url_abs":"http://arxiv.org/abs/1804.01967v1","url_pdf":"http://arxiv.org/pdf/1804.01967v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cbmv-a-coalesced-bidirectional-matching","repo_url":"https://github.com/kbatsos/CBMV","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"disparity-estimation","task_name":"Disparity Estimation"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"},{"task_slug":"stereo-matching","task_name":"Stereo Matching Hand"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}