{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U7UULCU65KI6HH4K3SC43BPUA7","short_pith_number":"pith:U7UULCU6","schema_version":"1.0","canonical_sha256":"a7e9458a9eea91e39f8adc85cd85f407ddf0b60dfddddd5675fe325098eefa35","source":{"kind":"arxiv","id":"2407.03168","version":2},"attestation_state":"computed","paper":{"title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingyun Zhang, Di Zhang, Jianzhu Guo, Pengfei Wan, Xiaoqiang Liu, Yuan Zhang, Zhizhou Zhong","submitted_at":"2024-07-03T14:41:39Z","abstract_excerpt":"Portrait Animation aims to synthesize a lifelike video from a single source image, using it as an appearance reference, with motion (i.e., facial expressions and head pose) derived from a driving video, audio, text, or generation. Instead of following mainstream diffusion-based methods, we explore and extend the potential of the implicit-keypoint-based framework, which effectively balances computational efficiency and controllability. Building upon this, we develop a video-driven portrait animation framework named LivePortrait with a focus on better generalization, controllability, and efficie"},"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":"2407.03168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T14:41:39Z","cross_cats_sorted":[],"title_canon_sha256":"ab8a69ed21a3516802454f58ac114901c263bb482585fe4c0949a81737e53592","abstract_canon_sha256":"e5fb37409a74a0c2d151a4f92c64e1c6180c473dd2ece4417f4db59af4ccf4dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:21.402174Z","signature_b64":"BzMLc/aP0qBpUhzaY3TSP4s3Exi+dANeBvL+dZTHc1FYgUp1+gvS0x9E0Z7ZYgM5+mQ7824Ld4G4GPdatYuUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7e9458a9eea91e39f8adc85cd85f407ddf0b60dfddddd5675fe325098eefa35","last_reissued_at":"2026-07-05T10:21:21.401661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:21.401661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingyun Zhang, Di Zhang, Jianzhu Guo, Pengfei Wan, Xiaoqiang Liu, Yuan Zhang, Zhizhou Zhong","submitted_at":"2024-07-03T14:41:39Z","abstract_excerpt":"Portrait Animation aims to synthesize a lifelike video from a single source image, using it as an appearance reference, with motion (i.e., facial expressions and head pose) derived from a driving video, audio, text, or generation. Instead of following mainstream diffusion-based methods, we explore and extend the potential of the implicit-keypoint-based framework, which effectively balances computational efficiency and controllability. Building upon this, we develop a video-driven portrait animation framework named LivePortrait with a focus on better generalization, controllability, and efficie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03168","kind":"arxiv","version":2},"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/2407.03168/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":"2407.03168","created_at":"2026-07-05T10:21:21.401720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03168v2","created_at":"2026-07-05T10:21:21.401720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03168","created_at":"2026-07-05T10:21:21.401720+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7UULCU65KI6","created_at":"2026-07-05T10:21:21.401720+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7UULCU65KI6HH4K","created_at":"2026-07-05T10:21:21.401720+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7UULCU6","created_at":"2026-07-05T10:21:21.401720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21657","citing_title":"Chehre: An Emoji-Prompted Video Dataset for Perceptually Diverse Facial Expression Recognition","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03402","citing_title":"Mamba-Enhanced Implicit Motion Learning for Audio-Driven Portrait Animation","ref_index":17,"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":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01031","citing_title":"Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30894","citing_title":"SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31088","citing_title":"Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24176","citing_title":"Loki: Representation over Architecture for Diffusion-Based Portrait Animation","ref_index":5,"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":10,"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":18,"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":17,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07603","citing_title":"UIKA: Fast Universal Head Avatar from Pose-Free Images","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22051","citing_title":"EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23552","citing_title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04434","citing_title":"Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12052","citing_title":"FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03548","citing_title":"Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10955","citing_title":"Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14594","citing_title":"TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10079","citing_title":"SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10334","citing_title":"The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23586","citing_title":"Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22865","citing_title":"MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction","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":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12255","citing_title":"ARGen: Affect-Reinforced Generative Augmentation towards Vision-based Dynamic Emotion Perception","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7UULCU65KI6HH4K3SC43BPUA7","json":"https://pith.science/pith/U7UULCU65KI6HH4K3SC43BPUA7.json","graph_json":"https://pith.science/api/pith-number/U7UULCU65KI6HH4K3SC43BPUA7/graph.json","events_json":"https://pith.science/api/pith-number/U7UULCU65KI6HH4K3SC43BPUA7/events.json","paper":"https://pith.science/paper/U7UULCU6"},"agent_actions":{"view_html":"https://pith.science/pith/U7UULCU65KI6HH4K3SC43BPUA7","download_json":"https://pith.science/pith/U7UULCU65KI6HH4K3SC43BPUA7.json","view_paper":"https://pith.science/paper/U7UULCU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03168&json=true","fetch_graph":"https://pith.science/api/pith-number/U7UULCU65KI6HH4K3SC43BPUA7/graph.json","fetch_events":"https://pith.science/api/pith-number/U7UULCU65KI6HH4K3SC43BPUA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7UULCU65KI6HH4K3SC43BPUA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7UULCU65KI6HH4K3SC43BPUA7/action/storage_attestation","attest_author":"https://pith.science/pith/U7UULCU65KI6HH4K3SC43BPUA7/action/author_attestation","sign_citation":"https://pith.science/pith/U7UULCU65KI6HH4K3SC43BPUA7/action/citation_signature","submit_replication":"https://pith.science/pith/U7UULCU65KI6HH4K3SC43BPUA7/action/replication_record"}},"created_at":"2026-07-05T10:21:21.401720+00:00","updated_at":"2026-07-05T10:21:21.401720+00:00"}