{"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/production-level-facial-performance-capture","title":"Production-Level Facial Performance Capture Using Deep Convolutional Neural Networks","arxiv_id":"1609.06536","date":"2016-09-21","proceeding":null,"authors":["Samuli Laine","Tero Karras","Timo Aila","Antti Herva","Shunsuke Saito","Ronald Yu","Hao Li","Jaakko Lehtinen"],"abstract":"We present a real-time deep learning framework for video-based facial\nperformance capture -- the dense 3D tracking of an actor's face given a\nmonocular video. Our pipeline begins with accurately capturing a subject using\na high-end production facial capture pipeline based on multi-view stereo\ntracking and artist-enhanced animations. With 5-10 minutes of captured footage,\nwe train a convolutional neural network to produce high-quality output,\nincluding self-occluded regions, from a monocular video sequence of that\nsubject. Since this 3D facial performance capture is fully automated, our\nsystem can drastically reduce the amount of labor involved in the development\nof modern narrative-driven video games or films involving realistic digital\ndoubles of actors and potentially hours of animated dialogue per character. We\ncompare our results with several state-of-the-art monocular real-time facial\ncapture techniques and demonstrate compelling animation inference in\nchallenging areas such as eyes and lips.","url_abs":"http://arxiv.org/abs/1609.06536v2","url_pdf":"http://arxiv.org/pdf/1609.06536v2.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":"production-level-facial-performance-capture","repo_url":"https://github.com/xianyuMeng/FacialCapture","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1609.06536","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}