{"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/the-fast-bilateral-solver","title":"The Fast Bilateral Solver","arxiv_id":"1511.03296","date":"2015-11-10","proceeding":null,"authors":["Jonathan T. Barron","Ben Poole"],"abstract":"We present the bilateral solver, a novel algorithm for edge-aware smoothing\nthat combines the flexibility and speed of simple filtering approaches with the\naccuracy of domain-specific optimization algorithms. Our technique is capable\nof matching or improving upon state-of-the-art results on several different\ncomputer vision tasks (stereo, depth superresolution, colorization, and\nsemantic segmentation) while being 10-1000 times faster than competing\napproaches. The bilateral solver is fast, robust, straightforward to generalize\nto new domains, and simple to integrate into deep learning pipelines.","url_abs":"http://arxiv.org/abs/1511.03296v2","url_pdf":"http://arxiv.org/pdf/1511.03296v2.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":"the-fast-bilateral-solver","repo_url":"https://github.com/kuan-wang/The_Bilateral_Solver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"the-fast-bilateral-solver","repo_url":"https://github.com/poolio/bilateral_solver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"the-fast-bilateral-solver","repo_url":"https://github.com/sampl-weizmann/deepcut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1511.03296","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}