{"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/discohead-audio-and-video-driven-talking-head","title":"DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions","arxiv_id":"2303.07697","date":"2023-03-14","proceeding":null,"authors":["Geumbyeol Hwang","Sunwon Hong","SeungHyun Lee","Sungwoo Park","Gyeongsu Chae"],"abstract":"For realistic talking head generation, creating natural head motion while maintaining accurate lip synchronization is essential. To fulfill this challenging task, we propose DisCoHead, a novel method to disentangle and control head pose and facial expressions without supervision. DisCoHead uses a single geometric transformation as a bottleneck to isolate and extract head motion from a head-driving video. Either an affine or a thin-plate spline transformation can be used and both work well as geometric bottlenecks. We enhance the efficiency of DisCoHead by integrating a dense motion estimator and the encoder of a generator which are originally separate modules. Taking a step further, we also propose a neural mix approach where dense motion is estimated and applied implicitly by the encoder. After applying the disentangled head motion to a source identity, DisCoHead controls the mouth region according to speech audio, and it blinks eyes and moves eyebrows following a separate driving video of the eye region, via the weight modulation of convolutional neural networks. The experiments using multiple datasets show that DisCoHead successfully generates realistic audio-and-video-driven talking heads and outperforms state-of-the-art methods. Project page: https://deepbrainai-research.github.io/discohead/","url_abs":"https://arxiv.org/abs/2303.07697v1","url_pdf":"https://arxiv.org/pdf/2303.07697v1.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":"discohead-audio-and-video-driven-talking-head","repo_url":"https://github.com/deepbrainai-research/koeba","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"talking-head-generation","task_name":"Talking Head Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.07697","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}