{"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/coarse-to-fine-lifted-map-inference-in","title":"Coarse-to-Fine Lifted MAP Inference in Computer Vision","arxiv_id":"1707.07165","date":"2017-07-22","proceeding":null,"authors":["Haroun Habeeb","Ankit Anand","Mausam","Parag Singla"],"abstract":"There is a vast body of theoretical research on lifted inference in\nprobabilistic graphical models (PGMs). However, few demonstrations exist where\nlifting is applied in conjunction with top of the line applied algorithms. We\npursue the applicability of lifted inference for computer vision (CV), with the\ninsight that a globally optimal (MAP) labeling will likely have the same label\nfor two symmetric pixels. The success of our approach lies in efficiently\nhandling a distinct unary potential on every node (pixel), typical of CV\napplications. This allows us to lift the large class of algorithms that model a\nCV problem via PGM inference. We propose a generic template for coarse-to-fine\n(C2F) inference in CV, which progressively refines an initial coarsely lifted\nPGM for varying quality-time trade-offs. We demonstrate the performance of C2F\ninference by developing lifted versions of two near state-of-the-art CV\nalgorithms for stereo vision and interactive image segmentation. We find that,\nagainst flat algorithms, the lifted versions have a much superior anytime\nperformance, without any loss in final solution quality.","url_abs":"http://arxiv.org/abs/1707.07165v1","url_pdf":"http://arxiv.org/pdf/1707.07165v1.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":"coarse-to-fine-lifted-map-inference-in","repo_url":"https://github.com/dair-iitd/c2fi4cv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"pgm","method_name":"PGM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}