{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4HNGDW7WOBUCKDT2UOSUYX2S2N","short_pith_number":"pith:4HNGDW7W","schema_version":"1.0","canonical_sha256":"e1da61dbf67068250e7aa3a54c5f52d3696b1f8cfe0392f58a9176cb775cc141","source":{"kind":"arxiv","id":"2403.17694","version":1},"attestation_state":"computed","paper":{"title":"AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","eess.IV"],"primary_cat":"cs.CV","authors_text":"Huawei Wei, Zejun Yang, Zhisheng Wang","submitted_at":"2024-03-26T13:35:02Z","abstract_excerpt":"In this study, we propose AniPortrait, a novel framework for generating high-quality animation driven by audio and a reference portrait image. Our methodology is divided into two stages. Initially, we extract 3D intermediate representations from audio and project them into a sequence of 2D facial landmarks. Subsequently, we employ a robust diffusion model, coupled with a motion module, to convert the landmark sequence into photorealistic and temporally consistent portrait animation. Experimental results demonstrate the superiority of AniPortrait in terms of facial naturalness, pose diversity, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.17694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T13:35:02Z","cross_cats_sorted":["cs.GR","eess.IV"],"title_canon_sha256":"33384b009ea17500acd19b2e10094f17bcbf3934abdcc5ef48f64d673bc12dc1","abstract_canon_sha256":"a05129358a4304020da69b0364176700f7e6ab2b9dd95f7a487466c9541cd211"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:54.454181Z","signature_b64":"E9sOQZrnlALx3weFP0r/kx7maRUC1eudTYDtCaGZ7bgf5b8Ow/pHxopmi9jifDcehVCIeyIinjqw8wKDl6mhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1da61dbf67068250e7aa3a54c5f52d3696b1f8cfe0392f58a9176cb775cc141","last_reissued_at":"2026-07-05T08:00:54.453742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:54.453742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","eess.IV"],"primary_cat":"cs.CV","authors_text":"Huawei Wei, Zejun Yang, Zhisheng Wang","submitted_at":"2024-03-26T13:35:02Z","abstract_excerpt":"In this study, we propose AniPortrait, a novel framework for generating high-quality animation driven by audio and a reference portrait image. Our methodology is divided into two stages. Initially, we extract 3D intermediate representations from audio and project them into a sequence of 2D facial landmarks. Subsequently, we employ a robust diffusion model, coupled with a motion module, to convert the landmark sequence into photorealistic and temporally consistent portrait animation. Experimental results demonstrate the superiority of AniPortrait in terms of facial naturalness, pose diversity, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17694","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.17694/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.17694","created_at":"2026-07-05T08:00:54.453798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17694v1","created_at":"2026-07-05T08:00:54.453798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17694","created_at":"2026-07-05T08:00:54.453798+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HNGDW7WOBUC","created_at":"2026-07-05T08:00:54.453798+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HNGDW7WOBUCKDT2","created_at":"2026-07-05T08:00:54.453798+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HNGDW7W","created_at":"2026-07-05T08:00:54.453798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03402","citing_title":"Mamba-Enhanced Implicit Motion Learning for Audio-Driven Portrait Animation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01620","citing_title":"Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01031","citing_title":"Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30849","citing_title":"SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24176","citing_title":"Loki: Representation over Architecture for Diffusion-Based Portrait Animation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25488","citing_title":"Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28056","citing_title":"CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30311","citing_title":"Archon: A Unified Multimodal Model for Holistic Digital Human Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30230","citing_title":"IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2411.16748","citing_title":"Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2411.09209","citing_title":"JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07603","citing_title":"UIKA: Fast Universal Head Avatar from Pose-Free Images","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23552","citing_title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12052","citing_title":"FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13669","citing_title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02948","citing_title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19679","citing_title":"MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19129","citing_title":"PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12856","citing_title":"PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08405","citing_title":"SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02948","citing_title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04787","citing_title":"AvatarPointillist: AutoRegressive 4D Gaussian Avatarization","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HNGDW7WOBUCKDT2UOSUYX2S2N","json":"https://pith.science/pith/4HNGDW7WOBUCKDT2UOSUYX2S2N.json","graph_json":"https://pith.science/api/pith-number/4HNGDW7WOBUCKDT2UOSUYX2S2N/graph.json","events_json":"https://pith.science/api/pith-number/4HNGDW7WOBUCKDT2UOSUYX2S2N/events.json","paper":"https://pith.science/paper/4HNGDW7W"},"agent_actions":{"view_html":"https://pith.science/pith/4HNGDW7WOBUCKDT2UOSUYX2S2N","download_json":"https://pith.science/pith/4HNGDW7WOBUCKDT2UOSUYX2S2N.json","view_paper":"https://pith.science/paper/4HNGDW7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17694&json=true","fetch_graph":"https://pith.science/api/pith-number/4HNGDW7WOBUCKDT2UOSUYX2S2N/graph.json","fetch_events":"https://pith.science/api/pith-number/4HNGDW7WOBUCKDT2UOSUYX2S2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HNGDW7WOBUCKDT2UOSUYX2S2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HNGDW7WOBUCKDT2UOSUYX2S2N/action/storage_attestation","attest_author":"https://pith.science/pith/4HNGDW7WOBUCKDT2UOSUYX2S2N/action/author_attestation","sign_citation":"https://pith.science/pith/4HNGDW7WOBUCKDT2UOSUYX2S2N/action/citation_signature","submit_replication":"https://pith.science/pith/4HNGDW7WOBUCKDT2UOSUYX2S2N/action/replication_record"}},"created_at":"2026-07-05T08:00:54.453798+00:00","updated_at":"2026-07-05T08:00:54.453798+00:00"}