{"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/efficient-inference-in-fully-connected-crfs","title":"Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials","arxiv_id":"1210.5644","date":"2012-10-20","proceeding":null,"authors":["Philipp Krähenbühl","Vladlen Koltun"],"abstract":"Most state-of-the-art techniques for multi-class image segmentation and\nlabeling use conditional random fields defined over pixels or image regions.\nWhile region-level models often feature dense pairwise connectivity,\npixel-level models are considerably larger and have only permitted sparse graph\nstructures. In this paper, we consider fully connected CRF models defined on\nthe complete set of pixels in an image. The resulting graphs have billions of\nedges, making traditional inference algorithms impractical. Our main\ncontribution is a highly efficient approximate inference algorithm for fully\nconnected CRF models in which the pairwise edge potentials are defined by a\nlinear combination of Gaussian kernels. Our experiments demonstrate that dense\nconnectivity at the pixel level substantially improves segmentation and\nlabeling accuracy.","url_abs":"http://arxiv.org/abs/1210.5644v1","url_pdf":"http://arxiv.org/pdf/1210.5644v1.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":"efficient-inference-in-fully-connected-crfs","repo_url":"https://github.com/Jasonlee1995/DeepLab_v1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"efficient-inference-in-fully-connected-crfs","repo_url":"https://github.com/johnnylu305/Simple-does-it-weakly-supervised-instance-and-semantic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"efficient-inference-in-fully-connected-crfs","repo_url":"https://github.com/plusmultiply/mprm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"crf","method_name":"CRF"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1210.5644","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}