{"url":"/task/3d-face-animation","name":"3D Face Animation","slug":"3d-face-animation","description_markdown":"Image: [Cudeiro et al](https://arxiv.org/pdf/1905.03079v1.pdf)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":34,"papers_with_code":25,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":6,"subtasks":1,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/3d-face-animation-on-beat2","slug":"3d-face-animation-on-beat2","dataset":"BEAT2","dataset_url":"/dataset/beat2","rows_in_archive":5,"metrics":["MSE"],"first_row_in_archive_order":{"model":"MambaTalk","paper_title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","paper_url":"/paper/mambatalk-efficient-holistic-gesture","paper_date":"2024-03-14","arxiv_id":"2403.09471","code_links":[{"title":"kkakkkka/MambaTalk","url":"https://github.com/kkakkkka/MambaTalk"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-face-animation-on-biwi-3d-audiovisual","slug":"3d-face-animation-on-biwi-3d-audiovisual","dataset":"Biwi 3D Audiovisual Corpus of Affective Communication - B3D(AC)^2","dataset_url":"/dataset/biwi-3d-audiovisual-corpus-of-affective","rows_in_archive":5,"metrics":["Lip Vertex Error","FDD"],"first_row_in_archive_order":{"model":"SelfTalk","paper_title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","paper_url":"/paper/selftalk-a-self-supervised-commutative","paper_date":"2023-06-19","arxiv_id":"2306.10799","code_links":[{"title":"psyai-net/SelfTalk_release","url":"https://github.com/psyai-net/SelfTalk_release"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}}},{"leaderboard":"/sota/3d-face-animation-on-vocaset","slug":"3d-face-animation-on-vocaset","dataset":"VOCASET","dataset_url":"/dataset/vocaset","rows_in_archive":2,"metrics":["Lip Vertex Error"],"first_row_in_archive_order":{"model":"FaceFormer","paper_title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","paper_url":"/paper/faceformer-speech-driven-3d-facial-animation","paper_date":"2021-12-10","arxiv_id":"2112.05329","code_links":[{"title":"EvelynFan/FaceFormer","url":"https://github.com/EvelynFan/FaceFormer"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/pascal-voc","name":"PASCAL VOC","full_name":"PASCAL Visual Object Classes Challenge","num_papers_in_archive":198},{"url":"/dataset/vocaset","name":"VOCASET","full_name":"VOCASET","num_papers_in_archive":60},{"url":"/dataset/beat2","name":"BEAT2","full_name":"BEAT-SMPLX-FLAME","num_papers_in_archive":23},{"url":"/dataset/biwi-3d-audiovisual-corpus-of-affective","name":"Biwi 3D Audiovisual Corpus of Affective Communication - B3D(AC)^2","full_name":"BIWI 3D","num_papers_in_archive":5},{"url":"/dataset/feafa","name":"FEAFA+","full_name":"","num_papers_in_archive":3},{"url":"/dataset/coma-1","name":"Human Optical Flow","full_name":"Human Optical Flow dataset","num_papers_in_archive":3}],"subtasks":[{"url":"/task/video-super-resolution","name":"Video Super-Resolution"}],"parent_tasks":[{"url":"/task/2d-human-pose-estimation","name":"2D Human Pose Estimation"},{"url":"/task/3d-absolute-human-pose-estimation","name":"3D Absolute Human Pose Estimation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":25,"of":25,"tagged_in_all":34,"items":[{"url":"/paper/learning-a-model-of-facial-shape-and","title":"Learning a model of facial shape and expression from 4D scans","date":"2017-11-01","arxiv_id":null,"repositories_listed":9,"syntology":null},{"url":"/paper/generating-holistic-3d-human-motion-from","title":"Generating Holistic 3D Human Motion from Speech","date":"2022-12-08","arxiv_id":"2212.04420","repositories_listed":3,"syntology":null},{"url":"/paper/emotalk-speech-driven-emotional","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","date":"2023-03-20","arxiv_id":"2303.11089","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":7}},{"url":"/paper/meshtalk-3d-face-animation-from-speech-using","title":"MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement","date":"2021-04-16","arxiv_id":"2104.08223","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/learning-an-animatable-detailed-3d-face-model","title":"Learning an Animatable Detailed 3D Face Model from In-The-Wild Images","date":"2020-12-07","arxiv_id":"2012.04012","repositories_listed":2,"syntology":null},{"url":"/paper/diffusiontalker-efficient-and-compact-speech","title":"DiffusionTalker: Efficient and Compact Speech-Driven 3D Talking Head via Personalizer-Guided Distillation","date":"2025-03-23","arxiv_id":"2503.18159","repositories_listed":1,"syntology":null},{"url":"/paper/cosmos-reason1-from-physical-common-sense-to","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","date":"2025-03-18","arxiv_id":"2503.15558","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/emoface-audio-driven-emotional-3d-face","title":"EmoFace: Audio-driven Emotional 3D Face Animation","date":"2024-07-17","arxiv_id":"2407.12501","repositories_listed":1,"syntology":null},{"url":"/paper/lego-leveraging-a-surface-deformation-network","title":"LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example","date":"2024-03-22","arxiv_id":"2403.15227","repositories_listed":1,"syntology":null},{"url":"/paper/mambatalk-efficient-holistic-gesture","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","date":"2024-03-14","arxiv_id":"2403.09471","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/emage-towards-unified-holistic-co-speech","title":"EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling","date":"2023-12-31","arxiv_id":"2401.00374","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/facetalk-audio-driven-motion-diffusion-for","title":"FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models","date":"2023-12-13","arxiv_id":"2312.08459","repositories_listed":1,"syntology":null},{"url":"/paper/facediffuser-speech-driven-3d-facial","title":"FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion","date":"2023-09-20","arxiv_id":"2309.11306","repositories_listed":1,"syntology":null},{"url":"/paper/speech-driven-3d-face-animation-with","title":"Speech-Driven 3D Face Animation with Composite and Regional Facial Movements","date":"2023-08-10","arxiv_id":"2308.05428","repositories_listed":1,"syntology":null},{"url":"/paper/selftalk-a-self-supervised-commutative","title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","date":"2023-06-19","arxiv_id":"2306.10799","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/learning-landmarks-motion-from-speech-for","title":"Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation","date":"2023-06-02","arxiv_id":"2306.01415","repositories_listed":1,"syntology":null},{"url":"/paper/mmface4d-a-large-scale-multi-modal-4d-face","title":"MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation","date":"2023-03-17","arxiv_id":"2303.09797","repositories_listed":1,"syntology":null},{"url":"/paper/facexhubert-text-less-speech-driven-e-x","title":"FaceXHuBERT: Text-less Speech-driven E(X)pressive 3D Facial Animation Synthesis Using Self-Supervised Speech Representation Learning","date":"2023-03-09","arxiv_id":"2303.05416","repositories_listed":1,"syntology":null},{"url":"/paper/codetalker-speech-driven-3d-facial-animation","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","date":"2023-01-06","arxiv_id":"2301.02379","repositories_listed":1,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/explicitly-controllable-3d-aware-portrait","title":"3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation","date":"2022-09-12","arxiv_id":"2209.05434","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/faceformer-speech-driven-3d-facial-animation","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","date":"2021-12-10","arxiv_id":"2112.05329","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/facial-synthesizing-dynamic-talking-face-with","title":"FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning","date":"2021-08-18","arxiv_id":"2108.07938","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/audio-driven-talking-face-video-generation","title":"Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose","date":"2020-02-24","arxiv_id":"2002.10137","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/capture-learning-and-synthesis-of-3d-speaking","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","date":"2019-05-08","arxiv_id":"1905.03079","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/3d-faces-in-motion-fully-automatic","title":"3D faces in motion: Fully automatic registration and statistical analysis","date":"2014-06-24","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}