{"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/is-a-green-screen-really-necessary-for-real","title":"MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition","arxiv_id":"2011.11961","date":"2020-11-24","proceeding":null,"authors":["Zhanghan Ke","Jiayu Sun","Kaican Li","Qiong Yan","Rynson W. H. Lau"],"abstract":"Existing portrait matting methods either require auxiliary inputs that are costly to obtain or involve multiple stages that are computationally expensive, making them less suitable for real-time applications. In this work, we present a light-weight matting objective decomposition network (MODNet) for portrait matting in real-time with a single input image. The key idea behind our efficient design is by optimizing a series of sub-objectives simultaneously via explicit constraints. In addition, MODNet includes two novel techniques for improving model efficiency and robustness. First, an Efficient Atrous Spatial Pyramid Pooling (e-ASPP) module is introduced to fuse multi-scale features for semantic estimation. Second, a self-supervised sub-objectives consistency (SOC) strategy is proposed to adapt MODNet to real-world data to address the domain shift problem common to trimap-free methods. MODNet is easy to be trained in an end-to-end manner. It is much faster than contemporaneous methods and runs at 67 frames per second on a 1080Ti GPU. Experiments show that MODNet outperforms prior trimap-free methods by a large margin on both Adobe Matting Dataset and a carefully designed photographic portrait matting (PPM-100) benchmark proposed by us. Further, MODNet achieves remarkable results on daily photos and videos. Our code and models are available at https://github.com/ZHKKKe/MODNet, and the PPM-100 benchmark is released at https://github.com/ZHKKKe/PPM.","url_abs":"https://arxiv.org/abs/2011.11961v4","url_pdf":"https://arxiv.org/pdf/2011.11961v4.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":"is-a-green-screen-really-necessary-for-real","repo_url":"https://github.com/ZHKKKe/MODNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"is-a-green-screen-really-necessary-for-real","repo_url":"https://github.com/ZHKKKe/PPM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"is-a-green-screen-really-necessary-for-real","repo_url":"https://github.com/DeepranjanG/Image_Background_Removal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"is-a-green-screen-really-necessary-for-real","repo_url":"https://github.com/royshil/obs-backgroundremoval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"unanswered"}},{"paper_slug":"is-a-green-screen-really-necessary-for-real","repo_url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/MODNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"is-a-green-screen-really-necessary-for-real","repo_url":"https://github.com/MS-Mind/MS-Code-08/tree/main/MODNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"is-a-green-screen-really-necessary-for-real","repo_url":"https://github.com/Mind23-2/MindCode-101/tree/main/MODNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"is-a-green-screen-really-necessary-for-real","repo_url":"https://github.com/PaddlePaddle/PaddleSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"is-a-green-screen-really-necessary-for-real","repo_url":"https://github.com/code-implementation1/Code5/tree/main/MODNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-matting","task_name":"Image Matting"},{"task_slug":"video-matting","task_name":"Video Matting"}],"methods":[{"method_slug":"modnet","method_name":"MODNet"}],"datasets_introduced":[{"slug":"phm-100","name":"PPM-100","full_name":""}],"methods_introduced":[{"slug":"modnet","name":"MODNet","full_name":"MODNet"}],"results":[{"leaderboard":"/sota/image-matting-on-amd","task":"Image Matting","dataset":"AMD","model":"MODNet+","rank_in_archive_order":1,"of":1,"metrics":{"MAD":"0.81","MSE":"0.0024"},"uses_additional_data":false},{"leaderboard":"/sota/image-matting-on-phm-100","task":"Image Matting","dataset":"PPM-100","model":"MODNet+ (Our)","rank_in_archive_order":1,"of":1,"metrics":{"MAD":"0.97","MSE":"0.0046"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.11961","atlas_url":"https://app.syntology.ai/?focus=2011.11961","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}