{"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/reflection-separation-using-guided-annotation","title":"Reflection Separation Using Guided Annotation","arxiv_id":"1702.05958","date":"2017-02-20","proceeding":null,"authors":["Ofer Springer","Yair Weiss"],"abstract":"Photographs taken through a glass surface often contain an approximately\nlinear superposition of reflected and transmitted layers. Decomposing an image\ninto these layers is generally an ill-posed task and the use of an additional\nimage prior and user provided cues is presently necessary in order to obtain\ngood results. Current annotation approaches rely on a strong sparsity\nassumption. For images with significant texture this assumption does not\ntypically hold, thus rendering the annotation process unviable. In this paper\nwe show that using a Gaussian Mixture Model patch prior, the correct local\ndecomposition can almost always be found as one of 100 likely modes of the\nposterior. Thus, the user need only choose one of these modes in a sparse set\nof patches and the decomposition may then be completed automatically. We\ndemonstrate the performance of our method using synthesized and real reflection\nimages.","url_abs":"http://arxiv.org/abs/1702.05958v2","url_pdf":"http://arxiv.org/pdf/1702.05958v2.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":"reflection-separation-using-guided-annotation","repo_url":"https://github.com/ofersp/refsep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}