{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/talking-head-generation","name":"Talking Head Generation","slug":"talking-head-generation","description_markdown":"Talking head generation is the task of generating a talking face from a set of images of a person.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Few-Shot Adversarial Learning of Realistic Neural Talking Head Models](https://arxiv.org/pdf/1905.08233v2.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":119,"papers_with_code":51,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":3,"subtasks":1,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/talking-head-generation-on-voxceleb2-1-shot","slug":"talking-head-generation-on-voxceleb2-1-shot","dataset":"VoxCeleb2 - 1-shot learning","dataset_url":"/dataset/voxceleb2","rows_in_archive":5,"metrics":["CSIM","LPIPS","Normalized Pose Error","SSIM","inference time (ms)","FID"],"first_row_in_archive_order":{"model":"Fast Bi-layer Avatars (medium size)","paper_title":"Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars","paper_url":"/paper/fast-bi-layer-neural-synthesis-of-one-shot","paper_date":"2020-08-24","arxiv_id":"2008.10174","code_links":[{"title":"saic-violet/bilayer-model","url":"https://github.com/saic-violet/bilayer-model"}],"syntology":null}},{"leaderboard":"/sota/talking-head-generation-on-voxceleb1-1-shot","slug":"talking-head-generation-on-voxceleb1-1-shot","dataset":"VoxCeleb1 - 1-shot learning","dataset_url":"/dataset/voxceleb1","rows_in_archive":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"Few-shot Adversarial Model","paper_title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","paper_url":"/paper/few-shot-adversarial-learning-of-realistic","paper_date":"2019-05-20","arxiv_id":"1905.08233","code_links":[{"title":"vincent-thevenin/Realistic-Neural-Talking-Head-Models","url":"https://github.com/vincent-thevenin/Realistic-Neural-Talking-Head-Models"},{"title":"grey-eye/talking-heads","url":"https://github.com/grey-eye/talking-heads"},{"title":"shoutOutYangJie/Few-Shot-Adversarial-Learning-for-face-swap","url":"https://github.com/shoutOutYangJie/Few-Shot-Adversarial-Learning-for-face-swap"},{"title":"ZVK/Talking-Heads","url":"https://github.com/ZVK/Talking-Heads"},{"title":"ZVK/talking_heads","url":"https://github.com/ZVK/talking_heads"},{"title":"Ierezell/PapierFewShot","url":"https://github.com/Ierezell/PapierFewShot"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-adversarial-learning-of-realistic#ran","syntology_url":"https://syntology.ai/paper/1905.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08233"}},"official":null}}},{"leaderboard":"/sota/talking-head-generation-on-voxceleb1-32-shot","slug":"talking-head-generation-on-voxceleb1-32-shot","dataset":"VoxCeleb1 - 32-shot learning","dataset_url":"/dataset/voxceleb1","rows_in_archive":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"Few-shot Adversarial Model","paper_title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","paper_url":"/paper/few-shot-adversarial-learning-of-realistic","paper_date":"2019-05-20","arxiv_id":"1905.08233","code_links":[{"title":"vincent-thevenin/Realistic-Neural-Talking-Head-Models","url":"https://github.com/vincent-thevenin/Realistic-Neural-Talking-Head-Models"},{"title":"grey-eye/talking-heads","url":"https://github.com/grey-eye/talking-heads"},{"title":"shoutOutYangJie/Few-Shot-Adversarial-Learning-for-face-swap","url":"https://github.com/shoutOutYangJie/Few-Shot-Adversarial-Learning-for-face-swap"},{"title":"ZVK/Talking-Heads","url":"https://github.com/ZVK/Talking-Heads"},{"title":"ZVK/talking_heads","url":"https://github.com/ZVK/talking_heads"},{"title":"Ierezell/PapierFewShot","url":"https://github.com/Ierezell/PapierFewShot"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-adversarial-learning-of-realistic#ran","syntology_url":"https://syntology.ai/paper/1905.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08233"}},"official":null}}},{"leaderboard":"/sota/talking-head-generation-on-voxceleb1-8-shot","slug":"talking-head-generation-on-voxceleb1-8-shot","dataset":"VoxCeleb1 - 8-shot learning","dataset_url":"/dataset/voxceleb1","rows_in_archive":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"Few-shot Adversarial Model","paper_title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","paper_url":"/paper/few-shot-adversarial-learning-of-realistic","paper_date":"2019-05-20","arxiv_id":"1905.08233","code_links":[{"title":"vincent-thevenin/Realistic-Neural-Talking-Head-Models","url":"https://github.com/vincent-thevenin/Realistic-Neural-Talking-Head-Models"},{"title":"grey-eye/talking-heads","url":"https://github.com/grey-eye/talking-heads"},{"title":"shoutOutYangJie/Few-Shot-Adversarial-Learning-for-face-swap","url":"https://github.com/shoutOutYangJie/Few-Shot-Adversarial-Learning-for-face-swap"},{"title":"ZVK/Talking-Heads","url":"https://github.com/ZVK/Talking-Heads"},{"title":"ZVK/talking_heads","url":"https://github.com/ZVK/talking_heads"},{"title":"Ierezell/PapierFewShot","url":"https://github.com/Ierezell/PapierFewShot"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-adversarial-learning-of-realistic#ran","syntology_url":"https://syntology.ai/paper/1905.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08233"}},"official":null}}},{"leaderboard":"/sota/talking-head-generation-on-voxceleb2-8-shot","slug":"talking-head-generation-on-voxceleb2-8-shot","dataset":"VoxCeleb2 - 8-shot learning","dataset_url":"/dataset/voxceleb2","rows_in_archive":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"CainGAN","paper_title":"Pose Manipulation with Identity Preservation","paper_url":"/paper/pose-manipulation-with-identity-preservation-1","paper_date":"2020-04-20","arxiv_id":"2004.09169","code_links":[],"syntology":null}},{"leaderboard":"/sota/talking-head-generation-on-100-sleep-nights","slug":"talking-head-generation-on-100-sleep-nights","dataset":"100 sleep nights of 8 caregivers","dataset_url":null,"rows_in_archive":1,"metrics":["10%"],"first_row_in_archive_order":{"model":"Ashok","paper_title":"0-Step Capturability, Motion Decomposition and Global Feedback Control of the 3D Variable Height-Inverted Pendulum","paper_url":"/paper/0-step-capturability-motion-decomposition-and","paper_date":"2019-12-12","arxiv_id":"1912.06078","code_links":[{"title":"GabrielEGC/IHMC-Robotics","url":"https://github.com/GabrielEGC/IHMC-Robotics"}],"syntology":null}},{"leaderboard":"/sota/talking-head-generation-on-voxceleb2-32-shot","slug":"talking-head-generation-on-voxceleb2-32-shot","dataset":"VoxCeleb2 - 32-shot learning","dataset_url":"/dataset/voxceleb2","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"Few-shot Adversarial Model","paper_title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","paper_url":"/paper/few-shot-adversarial-learning-of-realistic","paper_date":"2019-05-20","arxiv_id":"1905.08233","code_links":[{"title":"vincent-thevenin/Realistic-Neural-Talking-Head-Models","url":"https://github.com/vincent-thevenin/Realistic-Neural-Talking-Head-Models"},{"title":"grey-eye/talking-heads","url":"https://github.com/grey-eye/talking-heads"},{"title":"shoutOutYangJie/Few-Shot-Adversarial-Learning-for-face-swap","url":"https://github.com/shoutOutYangJie/Few-Shot-Adversarial-Learning-for-face-swap"},{"title":"ZVK/Talking-Heads","url":"https://github.com/ZVK/Talking-Heads"},{"title":"ZVK/talking_heads","url":"https://github.com/ZVK/talking_heads"},{"title":"Ierezell/PapierFewShot","url":"https://github.com/Ierezell/PapierFewShot"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-adversarial-learning-of-realistic#ran","syntology_url":"https://syntology.ai/paper/1905.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08233"}},"official":null}}}],"datasets":[{"url":"/dataset/voxceleb1","name":"VoxCeleb1","full_name":"VoxCeleb1","num_papers_in_archive":680},{"url":"/dataset/voxceleb2","name":"VoxCeleb2","full_name":"VoxCeleb2","num_papers_in_archive":564},{"url":"/dataset/animeceleb","name":"AnimeCeleb","full_name":"AnimeCeleb","num_papers_in_archive":2}],"subtasks":[{"url":"/task/lip-sync","name":"Unconstrained Lip-synchronization"}],"parent_tasks":[{"url":"/task/10-shot-image-generation","name":"10-shot image generation"},{"url":"/task/face-generation","name":"Face Generation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":119,"of_with_code":51,"tagged_in_all":119,"counts":{"archive_papers_tagged":119,"with_a_code_link":51,"where_syntology_ran_a_sample":11,"not_listed_spam_title":0,"listed":119,"listed_where_code_ran":11,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/few-shot-adversarial-learning-of-realistic","slug":"few-shot-adversarial-learning-of-realistic","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","date":"2019-05-20","arxiv_id":"1905.08233","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-adversarial-learning-of-realistic#ran","syntology_url":"https://syntology.ai/paper/1905.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08233"}},"official":null}},{"url":"/paper/a-lip-sync-expert-is-all-you-need-for-speech","slug":"a-lip-sync-expert-is-all-you-need-for-speech","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","date":"2020-08-23","arxiv_id":"2008.10010","repositories_listed":4,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-lip-sync-expert-is-all-you-need-for-speech#ran","syntology_url":"https://syntology.ai/paper/2008.10010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10010"}},"official":{"repos":["Rudrabha/Wav2Lip"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/makeittalk-speaker-aware-talking-head","slug":"makeittalk-speaker-aware-talking-head","title":"MakeItTalk: Speaker-Aware Talking-Head Animation","date":"2020-04-27","arxiv_id":"2004.12992","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/makeittalk-speaker-aware-talking-head#ran","syntology_url":"https://syntology.ai/paper/2004.12992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12992"}},"official":null}},{"url":"/paper/sadtalker-learning-realistic-3d-motion","slug":"sadtalker-learning-realistic-3d-motion","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","date":"2022-11-22","arxiv_id":"2211.12194","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-talking-head-generation-a","slug":"advancing-talking-head-generation-a","title":"Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions","date":"2025-06-23","arxiv_id":"2507.02900","repositories_listed":1,"syntology":null},{"url":"/paper/silence-is-golden-leveraging-adversarial","slug":"silence-is-golden-leveraging-adversarial","title":"Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generation","date":"2025-06-02","arxiv_id":"2506.01591","repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-controlled-video-diffusion-with","slug":"audio-visual-controlled-video-diffusion-with","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","date":"2025-04-03","arxiv_id":"2504.02542","repositories_listed":1,"syntology":null},{"url":"/paper/instag-learning-personalized-3d-talking-head","slug":"instag-learning-personalized-3d-talking-head","title":"InsTaG: Learning Personalized 3D Talking Head from Few-Second Video","date":"2025-02-27","arxiv_id":"2502.20387","repositories_listed":1,"syntology":null},{"url":"/paper/joint-co-speech-gesture-and-expressive","slug":"joint-co-speech-gesture-and-expressive","title":"Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters","date":"2024-12-18","arxiv_id":"2412.14333","repositories_listed":1,"syntology":null},{"url":"/paper/gohd-gaze-oriented-and-highly-disentangled","slug":"gohd-gaze-oriented-and-highly-disentangled","title":"GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expression","date":"2024-12-12","arxiv_id":"2412.09296","repositories_listed":1,"syntology":null},{"url":"/paper/comparative-analysis-of-audio-feature","slug":"comparative-analysis-of-audio-feature","title":"Comparative Analysis of Audio Feature Extraction for Real-Time Talking Portrait Synthesis","date":"2024-11-20","arxiv_id":"2411.13209","repositories_listed":1,"syntology":null},{"url":"/paper/dawn-dynamic-frame-avatar-with-non","slug":"dawn-dynamic-frame-avatar-with-non","title":"DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation","date":"2024-10-17","arxiv_id":"2410.13726","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-fixed-topologies-unregistered-training","slug":"beyond-fixed-topologies-unregistered-training","title":"Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads","date":"2024-10-14","arxiv_id":"2410.11041","repositories_listed":1,"syntology":null},{"url":"/paper/emodiffhead-continuously-emotional-control-in","slug":"emodiffhead-continuously-emotional-control-in","title":"EMOdiffhead: Continuously Emotional Control in Talking Head Generation via Diffusion","date":"2024-09-11","arxiv_id":"2409.07255","repositories_listed":1,"syntology":null},{"url":"/paper/moditalker-motion-disentangled-diffusion","slug":"moditalker-motion-disentangled-diffusion","title":"MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation","date":"2024-03-28","arxiv_id":"2403.19144","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-super-resolution-for-one-shot","slug":"adaptive-super-resolution-for-one-shot","title":"Adaptive Super Resolution For One-Shot Talking-Head Generation","date":"2024-03-23","arxiv_id":"2403.15944","repositories_listed":1,"syntology":null},{"url":"/paper/emovoca-speech-driven-emotional-3d-talking","slug":"emovoca-speech-driven-emotional-3d-talking","title":"EmoVOCA: Speech-Driven Emotional 3D Talking Heads","date":"2024-03-19","arxiv_id":"2403.12886","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-study-of-perceptual-quality","slug":"a-comparative-study-of-perceptual-quality","title":"A Comparative Study of Perceptual Quality Metrics for Audio-driven Talking Head Videos","date":"2024-03-11","arxiv_id":"2403.06421","repositories_listed":1,"syntology":null},{"url":"/paper/dreamtalk-when-expressive-talking-head","slug":"dreamtalk-when-expressive-talking-head","title":"DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models","date":"2023-12-15","arxiv_id":"2312.09767","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dreamtalk-when-expressive-talking-head#ran","syntology_url":"https://syntology.ai/paper/2312.09767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09767"}},"official":{"repos":["ali-vilab/dreamtalk"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/synctalk-the-devil-is-in-the-synchronization","slug":"synctalk-the-devil-is-in-the-synchronization","title":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","date":"2023-11-29","arxiv_id":"2311.17590","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/synctalk-the-devil-is-in-the-synchronization#ran","syntology_url":"https://syntology.ai/paper/2311.17590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17590"}},"official":{"repos":["ZiqiaoPeng/SyncTalk"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diffdub-person-generic-visual-dubbing-using","slug":"diffdub-person-generic-visual-dubbing-using","title":"DiffDub: Person-generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-encoder","date":"2023-11-03","arxiv_id":"2311.01811","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-emotional-adaptation-for-audio","slug":"efficient-emotional-adaptation-for-audio","title":"Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation","date":"2023-09-10","arxiv_id":"2309.04946","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/efficient-emotional-adaptation-for-audio#ran","syntology_url":"https://syntology.ai/paper/2309.04946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.04946"}},"official":{"repos":["yuangan/eat_code"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/text-to-video-a-two-stage-framework-for-zero","slug":"text-to-video-a-two-stage-framework-for-zero","title":"Text-to-Video: a Two-stage Framework for Zero-shot Identity-agnostic Talking-head Generation","date":"2023-08-12","arxiv_id":"2308.06457","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-identity-representation-conditioned","slug":"implicit-identity-representation-conditioned","title":"Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation","date":"2023-07-19","arxiv_id":"2307.09906","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/implicit-identity-representation-conditioned#ran","syntology_url":"https://syntology.ai/paper/2307.09906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09906"}},"official":{"repos":["harlanhong/iccv2023-mcnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-comprehensive-multi-scale-approach-for","slug":"a-comprehensive-multi-scale-approach-for","title":"A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation","date":"2023-07-04","arxiv_id":"2307.03270","repositories_listed":1,"syntology":null},{"url":"/paper/learning-landmarks-motion-from-speech-for","slug":"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/renderme-360-a-large-digital-asset-library-1","slug":"renderme-360-a-large-digital-asset-library-1","title":"RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars","date":"2023-05-22","arxiv_id":"2305.13353","repositories_listed":1,"syntology":null},{"url":"/paper/dagan-depth-aware-generative-adversarial","slug":"dagan-depth-aware-generative-adversarial","title":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","date":"2023-05-10","arxiv_id":"2305.06225","repositories_listed":1,"syntology":null},{"url":"/paper/face-animation-with-an-attribute-guided","slug":"face-animation-with-an-attribute-guided","title":"Face Animation with an Attribute-Guided Diffusion Model","date":"2023-04-06","arxiv_id":"2304.03199","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/face-animation-with-an-attribute-guided#ran","syntology_url":"https://syntology.ai/paper/2304.03199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03199"}},"official":{"repos":["zengbohan0217/fadm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/emotionally-enhanced-talking-face-generation","slug":"emotionally-enhanced-talking-face-generation","title":"Emotionally Enhanced Talking Face Generation","date":"2023-03-21","arxiv_id":"2303.11548","repositories_listed":1,"syntology":null},{"url":"/paper/discohead-audio-and-video-driven-talking-head","slug":"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","date":"2023-03-14","arxiv_id":"2303.07697","repositories_listed":1,"syntology":null},{"url":"/paper/difftalk-crafting-diffusion-models-for","slug":"difftalk-crafting-diffusion-models-for","title":"DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation","date":"2023-01-10","arxiv_id":"2301.03786","repositories_listed":1,"syntology":null},{"url":"/paper/styletalk-one-shot-talking-head-generation","slug":"styletalk-one-shot-talking-head-generation","title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles","date":"2023-01-03","arxiv_id":"2301.01081","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/styletalk-one-shot-talking-head-generation#ran","syntology_url":"https://syntology.ai/paper/2301.01081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.01081"}},"official":{"repos":["fuxivirtualhuman/styletalk"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/metaportrait-identity-preserving-talking-head","slug":"metaportrait-identity-preserving-talking-head","title":"MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation","date":"2022-12-15","arxiv_id":"2212.08062","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/metaportrait-identity-preserving-talking-head#ran","syntology_url":"https://syntology.ai/paper/2212.08062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08062"}},"official":{"repos":["Meta-Portrait/MetaPortrait"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/autoregressive-gan-for-semantic-unconditional","slug":"autoregressive-gan-for-semantic-unconditional","title":"Autoregressive GAN for Semantic Unconditional Head Motion Generation","date":"2022-11-02","arxiv_id":"2211.00987","repositories_listed":1,"syntology":null},{"url":"/paper/learning-dynamic-facial-radiance-fields-for","slug":"learning-dynamic-facial-radiance-fields-for","title":"Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis","date":"2022-07-24","arxiv_id":"2207.11770","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/learning-dynamic-facial-radiance-fields-for#ran","syntology_url":"https://syntology.ai/paper/2207.11770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.11770"}},"official":{"repos":["sstzal/DFRF"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/perceptual-conversational-head-generation","slug":"perceptual-conversational-head-generation","title":"Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer","date":"2022-06-26","arxiv_id":"2206.12837","repositories_listed":1,"syntology":null},{"url":"/paper/depth-aware-generative-adversarial-network","slug":"depth-aware-generative-adversarial-network","title":"Depth-Aware Generative Adversarial Network for Talking Head Video Generation","date":"2022-03-13","arxiv_id":"2203.06605","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/depth-aware-generative-adversarial-network#ran","syntology_url":"https://syntology.ai/paper/2203.06605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.06605"}},"official":{"repos":["harlanhong/cvpr2022-dagan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ai-generated-characters-for-supporting","slug":"ai-generated-characters-for-supporting","title":"AI-generated characters for supporting personalized learning and well-being","date":"2021-12-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/animeceleb-large-scale-animation-celebfaces","slug":"animeceleb-large-scale-animation-celebfaces","title":"AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment","date":"2021-11-15","arxiv_id":"2111.07640","repositories_listed":1,"syntology":null},{"url":"/paper/live-speech-portraits-real-time","slug":"live-speech-portraits-real-time","title":"Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation","date":"2021-09-22","arxiv_id":"2109.10595","repositories_listed":1,"syntology":null},{"url":"/paper/audio2head-audio-driven-one-shot-talking-head","slug":"audio2head-audio-driven-one-shot-talking-head","title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","date":"2021-07-20","arxiv_id":"2107.09293","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"0 ran · 5 unverified","sample_list":"/paper/audio2head-audio-driven-one-shot-talking-head#ran","syntology_url":"https://syntology.ai/paper/2107.09293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09293"}},"official":{"repos":["wangsuzhen/Audio2Head"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"url":"/paper/txt2vid-ultra-low-bitrate-compression-of","slug":"txt2vid-ultra-low-bitrate-compression-of","title":"Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text","date":"2021-06-26","arxiv_id":"2106.14014","repositories_listed":1,"syntology":null},{"url":"/paper/write-a-speaker-text-based-emotional-and","slug":"write-a-speaker-text-based-emotional-and","title":"Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation","date":"2021-04-16","arxiv_id":"2104.07995","repositories_listed":1,"syntology":null},{"url":"/paper/fast-bi-layer-neural-synthesis-of-one-shot","slug":"fast-bi-layer-neural-synthesis-of-one-shot","title":"Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars","date":"2020-08-24","arxiv_id":"2008.10174","repositories_listed":1,"syntology":null},{"url":"/paper/mead-a-large-scale-audio-visual-dataset-for","slug":"mead-a-large-scale-audio-visual-dataset-for","title":"MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/talking-head-generation-with-rhythmic-head","slug":"talking-head-generation-with-rhythmic-head","title":"Talking-head Generation with Rhythmic Head Motion","date":"2020-07-16","arxiv_id":"2007.08547","repositories_listed":1,"syntology":null},{"url":"/paper/what-comprises-a-good-talking-head-video","slug":"what-comprises-a-good-talking-head-video","title":"What comprises a good talking-head video generation?: A Survey and Benchmark","date":"2020-05-07","arxiv_id":"2005.03201","repositories_listed":1,"syntology":null},{"url":"/paper/neural-voice-puppetry-audio-driven-facial","slug":"neural-voice-puppetry-audio-driven-facial","title":"Neural Voice Puppetry: Audio-driven Facial Reenactment","date":"2019-12-11","arxiv_id":"1912.05566","repositories_listed":1,"syntology":null},{"url":"/paper/text-based-editing-of-talking-head-video","slug":"text-based-editing-of-talking-head-video","title":"Text-based Editing of Talking-head Video","date":"2019-06-04","arxiv_id":"1906.01524","repositories_listed":1,"syntology":null},{"url":"/paper/reenactgan-learning-to-reenact-faces-via","slug":"reenactgan-learning-to-reenact-faces-via","title":"ReenactGAN: Learning to Reenact Faces via Boundary Transfer","date":"2018-07-29","arxiv_id":"1807.11079","repositories_listed":1,"syntology":null},{"url":null,"slug":"medtalk-multimodal-controlled-3d-facial","title":"MEDTalk: Multimodal Controlled 3D Facial Animation with Dynamic Emotions by Disentangled Embedding","date":"2025-07-08","arxiv_id":"2507.06071","repositories_listed":0,"syntology":null},{"url":null,"slug":"dualtalk-dual-speaker-interaction-for-3d","title":"DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations","date":"2025-05-23","arxiv_id":"2505.18096","repositories_listed":0,"syntology":null},{"url":null,"slug":"keysync-a-robust-approach-for-leakage-free","title":"KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution","date":"2025-05-01","arxiv_id":"2505.00497","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnitalker-real-time-text-driven-talking-head","title":"OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication","date":"2025-04-03","arxiv_id":"2504.02433","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-plane-audio-factorization-plane","title":"Audio-Plane: Audio Factorization Plane Gaussian Splatting for Real-Time Talking Head Synthesis","date":"2025-03-28","arxiv_id":"2503.22605","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-audio-centric-modality-coupling-for","title":"Dual Audio-Centric Modality Coupling for Talking Head Generation","date":"2025-03-26","arxiv_id":"2503.22728","repositories_listed":0,"syntology":null},{"url":null,"slug":"perceptually-accurate-3d-talking-head","title":"Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics","date":"2025-03-26","arxiv_id":"2503.20308","repositories_listed":0,"syntology":null},{"url":null,"slug":"teller-real-time-streaming-audio-driven","title":"Teller: Real-Time Streaming Audio-Driven Portrait Animation with Autoregressive Motion Generation","date":"2025-03-24","arxiv_id":"2503.18429","repositories_listed":0,"syntology":null},{"url":null,"slug":"dimitra-audio-driven-diffusion-model-for","title":"Dimitra: Audio-driven Diffusion model for Expressive Talking Head Generation","date":"2025-02-24","arxiv_id":"2502.17198","repositories_listed":0,"syntology":null},{"url":null,"slug":"videoanydoor-high-fidelity-video-object","title":"VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control","date":"2025-01-02","arxiv_id":"2501.01427","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniavatar-taming-lifelike-audio-driven","title":"UniAvatar: Taming Lifelike Audio-Driven Talking Head Generation with Comprehensive Motion and Lighting Control","date":"2024-12-26","arxiv_id":"2412.19860","repositories_listed":0,"syntology":null},{"url":null,"slug":"vqtalker-towards-multilingual-talking-avatars","title":"VQTalker: Towards Multilingual Talking Avatars through Facial Motion Tokenization","date":"2024-12-13","arxiv_id":"2412.09892","repositories_listed":0,"syntology":null},{"url":null,"slug":"if-mdm-implicit-face-motion-diffusion-model","title":"IF-MDM: Implicit Face Motion Diffusion Model for High-Fidelity Realtime Talking Head Generation","date":"2024-12-05","arxiv_id":"2412.04000","repositories_listed":0,"syntology":null},{"url":null,"slug":"consistentavatar-learning-to-diffuse-fully","title":"ConsistentAvatar: Learning to Diffuse Fully Consistent Talking Head Avatar with Temporal Guidance","date":"2024-11-23","arxiv_id":"2411.15436","repositories_listed":0,"syntology":null},{"url":null,"slug":"emotivetalk-expressive-talking-head","title":"EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion","date":"2024-11-23","arxiv_id":"2411.16726","repositories_listed":0,"syntology":null},{"url":null,"slug":"les-talker-fine-grained-emotion-editing-for","title":"LES-Talker: Fine-Grained Emotion Editing for Talking Head Generation in Linear Emotion Space","date":"2024-11-14","arxiv_id":"2411.09268","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-driven-emotional-3d-talking-head","title":"EmoGene: Audio-Driven Emotional 3D Talking-Head Generation","date":"2024-10-07","arxiv_id":"2410.17262","repositories_listed":0,"syntology":null},{"url":null,"slug":"ladtalk-latent-denoising-for-synthesizing","title":"LaDTalk: Latent Denoising for Synthesizing Talking Head Videos with High Frequency Details","date":"2024-10-01","arxiv_id":"2410.00990","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-frame-wise-emotion-intensity-for","title":"Learning Frame-Wise Emotion Intensity for Audio-Driven Talking-Head Generation","date":"2024-09-29","arxiv_id":"2409.19501","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamhead-learning-spatial-temporal","title":"DreamHead: Learning Spatial-Temporal Correspondence via Hierarchical Diffusion for Audio-driven Talking Head Synthesis","date":"2024-09-16","arxiv_id":"2409.10281","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffted-one-shot-audio-driven-ted-talk-video","title":"DiffTED: One-shot Audio-driven TED Talk Video Generation with Diffusion-based Co-speech Gestures","date":"2024-09-11","arxiv_id":"2409.07649","repositories_listed":0,"syntology":null},{"url":null,"slug":"svp-style-enhanced-vivid-portrait-talking","title":"SVP: Style-Enhanced Vivid Portrait Talking Head Diffusion Model","date":"2024-09-05","arxiv_id":"2409.03270","repositories_listed":0,"syntology":null},{"url":null,"slug":"posetalk-text-and-audio-based-pose-control","title":"PoseTalk: Text-and-Audio-based Pose Control and Motion Refinement for One-Shot Talking Head Generation","date":"2024-09-04","arxiv_id":"2409.02657","repositories_listed":0,"syntology":null},{"url":null,"slug":"fd2talk-towards-generalized-talking-head","title":"FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion Model","date":"2024-08-18","arxiv_id":"2408.09384","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01732","title":"Landmark-guided Diffusion Model for High-fidelity and Temporally Coherent Talking Head Generation","date":"2024-08-03","arxiv_id":"2408.01732","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01826","title":"GLDiTalker: Speech-Driven 3D Facial Animation with Graph Latent Diffusion Transformer","date":"2024-08-03","arxiv_id":"2408.01826","repositories_listed":0,"syntology":null},{"url":null,"slug":"multitalk-enhancing-3d-talking-head","title":"MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset","date":"2024-06-20","arxiv_id":"2406.14272","repositories_listed":0,"syntology":null},{"url":null,"slug":"nldf-neural-light-dynamic-fields-for","title":"NLDF: Neural Light Dynamic Fields for Efficient 3D Talking Head Generation","date":"2024-06-17","arxiv_id":"2406.11259","repositories_listed":0,"syntology":null},{"url":null,"slug":"listen-disentangle-and-control-controllable","title":"SPEAK: Speech-Driven Pose and Emotion-Adjustable Talking Head Generation","date":"2024-05-12","arxiv_id":"2405.07257","repositories_listed":0,"syntology":null},{"url":null,"slug":"nerffacespeech-one-shot-audio-diven-3d","title":"NeRFFaceSpeech: One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior","date":"2024-05-09","arxiv_id":"2405.05749","repositories_listed":0,"syntology":null},{"url":null,"slug":"embedded-representation-learning-network-for","title":"Embedded Representation Learning Network for Animating Styled Video Portrait","date":"2024-04-29","arxiv_id":"2404.19038","repositories_listed":0,"syntology":null},{"url":null,"slug":"edtalk-efficient-disentanglement-for","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","date":"2024-04-02","arxiv_id":"2404.01647","repositories_listed":0,"syntology":null},{"url":null,"slug":"style2talker-high-resolution-talking-head","title":"Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style","date":"2024-03-11","arxiv_id":"2403.06365","repositories_listed":0,"syntology":null},{"url":null,"slug":"ae-nerf-audio-enhanced-neural-radiance-field","title":"AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis","date":"2023-12-18","arxiv_id":"2312.10921","repositories_listed":0,"syntology":null},{"url":null,"slug":"vectortalker-svg-talking-face-generation-with","title":"VectorTalker: SVG Talking Face Generation with Progressive Vectorisation","date":"2023-12-18","arxiv_id":"2312.11568","repositories_listed":0,"syntology":null},{"url":null,"slug":"pmmtalk-speech-driven-3d-facial-animation","title":"PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features","date":"2023-12-05","arxiv_id":"2312.02781","repositories_listed":0,"syntology":null},{"url":null,"slug":"vividtalk-one-shot-audio-driven-talking-head","title":"VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior","date":"2023-12-04","arxiv_id":"2312.01841","repositories_listed":0,"syntology":null},{"url":null,"slug":"laughtalk-expressive-3d-talking-head","title":"LaughTalk: Expressive 3D Talking Head Generation with Laughter","date":"2023-11-02","arxiv_id":"2311.00994","repositories_listed":0,"syntology":null},{"url":null,"slug":"osm-net-one-to-many-one-shot-talking-head","title":"OSM-Net: One-to-Many One-shot Talking Head Generation with Spontaneous Head Motions","date":"2023-09-28","arxiv_id":"2309.16148","repositories_listed":0,"syntology":null},{"url":null,"slug":"radio-reference-agnostic-dubbing-video","title":"RADIO: Reference-Agnostic Dubbing Video Synthesis","date":"2023-09-05","arxiv_id":"2309.01950","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-pixels-to-portraits-a-comprehensive","title":"From Pixels to Portraits: A Comprehensive Survey of Talking Head Generation Techniques and Applications","date":"2023-08-30","arxiv_id":"2308.16041","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-semantic-perceptual-listener","title":"Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline","date":"2023-07-19","arxiv_id":"2307.09821","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-conversational-head-generation","title":"Interactive Conversational Head Generation","date":"2023-07-05","arxiv_id":"2307.02090","repositories_listed":0,"syntology":null},{"url":null,"slug":"emotional-talking-head-generation-based-on","title":"Emotional Talking Head Generation based on Memory-Sharing and Attention-Augmented Networks","date":"2023-06-06","arxiv_id":"2306.03594","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-fidelity-and-freely-controllable-talking","title":"High-Fidelity and Freely Controllable Talking Head Video Generation","date":"2023-04-20","arxiv_id":"2304.10168","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-high-fidelity-talking-head-synthesis","title":"One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field","date":"2023-04-11","arxiv_id":"2304.05097","repositories_listed":0,"syntology":null},{"url":null,"slug":"talkclip-talking-head-generation-with-text","title":"TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles","date":"2023-04-01","arxiv_id":"2304.00334","repositories_listed":0,"syntology":null},{"url":null,"slug":"font-flow-guided-one-shot-talking-head","title":"FONT: Flow-guided One-shot Talking Head Generation with Natural Head Motions","date":"2023-03-31","arxiv_id":"2303.17789","repositories_listed":0,"syntology":null},{"url":null,"slug":"opt-one-shot-pose-controllable-talking-head","title":"OPT: One-shot Pose-Controllable Talking Head Generation","date":"2023-02-16","arxiv_id":"2302.08197","repositories_listed":0,"syntology":null}],"syntology_records":13,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":11,"papers_where_code_ran_first_page":"/task/talking-head-generation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/talking-head-generation/papers/2","json":"/task/talking-head-generation/papers/2.json","rows":19},{"order":"ran","page":1,"of":1,"url":"/task/talking-head-generation/papers/ran/1","json":"/task/talking-head-generation/papers/ran/1.json","rows":11}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"dcf685a3e6bbb12a392a1ad8a4b9eef93e142dea191807c2583caa4c25d39a7e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}