{"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/cross-scale-cost-aggregation-for-stereo","title":"Cross-Scale Cost Aggregation for Stereo Matching","arxiv_id":"1403.0316","date":"2014-03-03","proceeding":"CVPR 2014 6","authors":["Kang Zhang","Yuqiang Fang","Dongbo Min","Lifeng Sun","Shiqiang Yang. Shuicheng Yan","Qi Tian"],"abstract":"Human beings process stereoscopic correspondence across multiple scales.\nHowever, this bio-inspiration is ignored by state-of-the-art cost aggregation\nmethods for dense stereo correspondence. In this paper, a generic cross-scale\ncost aggregation framework is proposed to allow multi-scale interaction in cost\naggregation. We firstly reformulate cost aggregation from a unified\noptimization perspective and show that different cost aggregation methods\nessentially differ in the choices of similarity kernels. Then, an inter-scale\nregularizer is introduced into optimization and solving this new optimization\nproblem leads to the proposed framework. Since the regularization term is\nindependent of the similarity kernel, various cost aggregation methods can be\nintegrated into the proposed general framework. We show that the cross-scale\nframework is important as it effectively and efficiently expands\nstate-of-the-art cost aggregation methods and leads to significant\nimprovements, when evaluated on Middlebury, KITTI and New Tsukuba datasets.","url_abs":"http://arxiv.org/abs/1403.0316v1","url_pdf":"http://arxiv.org/pdf/1403.0316v1.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":"cross-scale-cost-aggregation-for-stereo","repo_url":"https://github.com/rookiepig/CrossScaleStereo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"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}