{"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/single-image-reflection-removal-using-deep","title":"Single Image Reflection Removal Using Deep Encoder-Decoder Network","arxiv_id":"1802.00094","date":"2018-01-31","proceeding":null,"authors":["Zhixiang Chi","Xiaolin Wu","Xiao Shu","Jinjin Gu"],"abstract":"Image of a scene captured through a piece of transparent and reflective\nmaterial, such as glass, is often spoiled by a superimposed layer of reflection\nimage. While separating the reflection from a familiar object in an image is\nmentally not difficult for humans, it is a challenging, ill-posed problem in\ncomputer vision. In this paper, we propose a novel deep convolutional\nencoder-decoder method to remove the objectionable reflection by learning a map\nbetween image pairs with and without reflection. For training the neural\nnetwork, we model the physical formation of reflections in images and\nsynthesize a large number of photo-realistic reflection-tainted images from\nreflection-free images collected online. Extensive experimental results show\nthat, although the neural network learns only from synthetic data, the proposed\nmethod is effective on real-world images, and it significantly outperforms the\nother tested state-of-the-art techniques.","url_abs":"http://arxiv.org/abs/1802.00094v1","url_pdf":"http://arxiv.org/pdf/1802.00094v1.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":"single-image-reflection-removal-using-deep","repo_url":"https://github.com/LastReLU/Reflection-Separation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"single-image-reflection-removal-using-deep","repo_url":"https://github.com/LastReLU/ReflectionSeparation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"single-image-reflection-removal-using-deep","repo_url":"https://github.com/sergevkim/ReflectionSeparation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"reflection-removal","task_name":"Reflection Removal"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}