{"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/adversarially-guided-portrait-matting","title":"Adversarially-Guided Portrait Matting","arxiv_id":"2305.02981","date":"2023-05-04","proceeding":null,"authors":["Sergej Chicherin","Karen Efremyan"],"abstract":"We present a method for generating alpha mattes using a limited data source. We pretrain a novel transformerbased model (StyleMatte) on portrait datasets. We utilize this model to provide image-mask pairs for the StyleGAN3-based network (StyleMatteGAN). This network is trained unsupervisedly and generates previously unseen imagemask training pairs that are fed back to StyleMatte. We demonstrate that the performance of the matte pulling network improves during this cycle and obtains top results on the human portraits and state-of-the-art metrics on animals dataset. Furthermore, StyleMatteGAN provides high-resolution, privacy-preserving portraits with alpha mattes, making it suitable for various image composition tasks. Our code is available at https://github.com/chroneus/stylematte","url_abs":"https://arxiv.org/abs/2305.02981v2","url_pdf":"https://arxiv.org/pdf/2305.02981v2.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":"adversarially-guided-portrait-matting","repo_url":"https://github.com/chroneus/stylematte","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-matting","task_name":"Image Matting"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-matting-on-am-2k","task":"Image Matting","dataset":"AM-2K","model":"StyleMatte","rank_in_archive_order":1,"of":9,"metrics":{"MAD":"0.0055","MSE":"0.0024","SAD":"9.602"},"uses_additional_data":false},{"leaderboard":"/sota/image-matting-on-p3m-10k","task":"Image Matting","dataset":"P3M-10k","model":"StyleMatte","rank_in_archive_order":2,"of":7,"metrics":{"MAD":"0.004","MSE":"0.0019","SAD":"6.97"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.02981","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}