{"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/background-matting-the-world-is-your-green","title":"Background Matting: The World is Your Green Screen","arxiv_id":"2004.00626","date":"2020-04-01","proceeding":"CVPR 2020 6","authors":["Soumyadip Sengupta","Vivek Jayaram","Brian Curless","Steve Seitz","Ira Kemelmacher-Shlizerman"],"abstract":"We propose a method for creating a matte -- the per-pixel foreground color and alpha -- of a person by taking photos or videos in an everyday setting with a handheld camera. Most existing matting methods require a green screen background or a manually created trimap to produce a good matte. Automatic, trimap-free methods are appearing, but are not of comparable quality. In our trimap free approach, we ask the user to take an additional photo of the background without the subject at the time of capture. This step requires a small amount of foresight but is far less time-consuming than creating a trimap. We train a deep network with an adversarial loss to predict the matte. We first train a matting network with supervised loss on ground truth data with synthetic composites. To bridge the domain gap to real imagery with no labeling, we train another matting network guided by the first network and by a discriminator that judges the quality of composites. We demonstrate results on a wide variety of photos and videos and show significant improvement over the state of the art.","url_abs":"https://arxiv.org/abs/2004.00626v2","url_pdf":"https://arxiv.org/pdf/2004.00626v2.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":"background-matting-the-world-is-your-green","repo_url":"https://github.com/senguptaumd/Background-Matting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-matting","task_name":"Image Matting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-matting-on-adobe-matting","task":"Image Matting","dataset":"Adobe Matting","model":"Adobe LS-GAN","rank_in_archive_order":1,"of":4,"metrics":{"MSE":"0.97","SAD":"1.72"},"uses_additional_data":false},{"leaderboard":"/sota/image-matting-on-adobe-matting","task":"Image Matting","dataset":"Adobe Matting","model":"IM","rank_in_archive_order":2,"of":4,"metrics":{"MSE":"1.16","SAD":"1.92"},"uses_additional_data":false},{"leaderboard":"/sota/image-matting-on-adobe-matting","task":"Image Matting","dataset":"Adobe Matting","model":"BM","rank_in_archive_order":3,"of":4,"metrics":{"MSE":"1.33","SAD":"2.53"},"uses_additional_data":false},{"leaderboard":"/sota/image-matting-on-adobe-matting","task":"Image Matting","dataset":"Adobe Matting","model":"CAM","rank_in_archive_order":4,"of":4,"metrics":{"MSE":"4.5","SAD":"3.67"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.00626","atlas_url":"https://app.syntology.ai/?focus=2004.00626","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}