{"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/geneface-generalized-and-high-fidelity-audio","title":"GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis","arxiv_id":"2301.13430","date":"2023-01-31","proceeding":null,"authors":["Zhenhui Ye","Ziyue Jiang","Yi Ren","Jinglin Liu","Jinzheng He","Zhou Zhao"],"abstract":"Generating photo-realistic video portrait with arbitrary speech audio is a crucial problem in film-making and virtual reality. Recently, several works explore the usage of neural radiance field in this task to improve 3D realness and image fidelity. However, the generalizability of previous NeRF-based methods to out-of-domain audio is limited by the small scale of training data. In this work, we propose GeneFace, a generalized and high-fidelity NeRF-based talking face generation method, which can generate natural results corresponding to various out-of-domain audio. Specifically, we learn a variaitional motion generator on a large lip-reading corpus, and introduce a domain adaptative post-net to calibrate the result. Moreover, we learn a NeRF-based renderer conditioned on the predicted facial motion. A head-aware torso-NeRF is proposed to eliminate the head-torso separation problem. Extensive experiments show that our method achieves more generalized and high-fidelity talking face generation compared to previous methods.","url_abs":"https://arxiv.org/abs/2301.13430v1","url_pdf":"https://arxiv.org/pdf/2301.13430v1.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":"geneface-generalized-and-high-fidelity-audio","repo_url":"https://github.com/yerfor/geneface","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"face-generation","task_name":"Face Generation"},{"task_slug":"lip-reading","task_name":"Lip Reading"},{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"talking-face-generation","task_name":"Talking Face Generation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.13430","atlas_url":"https://app.syntology.ai/?focus=2301.13430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13430"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yerfor/geneface","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":1,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"yerfor/geneface","repo_kind":"listed","path":"data_util/face_parsing/resnet.py","file_url":"https://github.com/yerfor/geneface/blob/HEAD/data_util/face_parsing/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"325b8d54f52e2421","entry":"create_layer_basic","repo":"yerfor/geneface","repo_kind":"listed","path":"data_util/face_parsing/resnet.py","file_url":"https://github.com/yerfor/geneface/blob/HEAD/data_util/face_parsing/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"325b8d54f52e2421"}},{"code_sha256_prefix":"2e9ce6a02832f7c8","entry":"perspective_projection","repo":"yerfor/geneface","repo_kind":"listed","path":"deep_3drecon/deep_3drecon_models/bfm.py","file_url":"https://github.com/yerfor/geneface/blob/HEAD/deep_3drecon/deep_3drecon_models/bfm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e9ce6a02832f7c8"}},{"code_sha256_prefix":"03e2c9d25851153d","entry":"save_transforms","repo":"yerfor/geneface","repo_kind":"listed","path":"data_util/process.py","file_url":"https://github.com/yerfor/geneface/blob/HEAD/data_util/process.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03e2c9d25851153d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}