{"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/gaussianspeech-audio-driven-gaussian-avatars","title":"GaussianSpeech: Audio-Driven Gaussian Avatars","arxiv_id":"2411.18675","date":"2024-11-27","proceeding":null,"authors":["Shivangi Aneja","Artem Sevastopolsky","Tobias Kirschstein","Justus Thies","Angela Dai","Matthias Nießner"],"abstract":"We introduce GaussianSpeech, a novel approach that synthesizes high-fidelity animation sequences of photo-realistic, personalized 3D human head avatars from spoken audio. To capture the expressive, detailed nature of human heads, including skin furrowing and finer-scale facial movements, we propose to couple speech signal with 3D Gaussian splatting to create realistic, temporally coherent motion sequences. We propose a compact and efficient 3DGS-based avatar representation that generates expression-dependent color and leverages wrinkle- and perceptually-based losses to synthesize facial details, including wrinkles that occur with different expressions. To enable sequence modeling of 3D Gaussian splats with audio, we devise an audio-conditioned transformer model capable of extracting lip and expression features directly from audio input. Due to the absence of high-quality datasets of talking humans in correspondence with audio, we captured a new large-scale multi-view dataset of audio-visual sequences of talking humans with native English accents and diverse facial geometry. GaussianSpeech consistently achieves state-of-the-art performance with visually natural motion at real time rendering rates, while encompassing diverse facial expressions and styles.","url_abs":"https://arxiv.org/abs/2411.18675v1","url_pdf":"https://arxiv.org/pdf/2411.18675v1.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":"gaussianspeech-audio-driven-gaussian-avatars","repo_url":"https://github.com/shivangi-aneja/GaussianSpeech","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3dgs","task_name":"3DGS"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.18675","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}