{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DF6UGGHY525M4UH3WAH4LMRVN3","short_pith_number":"pith:DF6UGGHY","schema_version":"1.0","canonical_sha256":"197d4318f8eebace50fbb00fc5b2356eca0485333efe18c99680de9f063c548a","source":{"kind":"arxiv","id":"2412.00733","version":4},"attestation_state":"computed","paper":{"title":"Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hang Zhou, Hanlin Shang, Hui Li, Jiahao Cui, Jingdong Wang, Kaihui Cheng, Shan Mu, Siyu Zhu, Yun Zhan, Yuqi Ma","submitted_at":"2024-12-01T08:54:30Z","abstract_excerpt":"Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait, and generating immersive, realistic backgrounds. In this paper, we introduce the first application of a pretrained transformer-based video generative model that demonstrates strong generalization capabilities and generates highly dynamic, realistic videos for portrait animation, effectively addressing these challenges. The adoption of a new video backbone model makes previous U-Net-based methods for identity maintena"},"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":"2412.00733","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T08:54:30Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"c61c58dcfb35729853777ac379b0fb845aaf5bfc3cad233fde2ba242a8f36725","abstract_canon_sha256":"756fb6f5a58c64951bf47ad779c904d3c9390850f0a41854cf805b7366e72268"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:27.563869Z","signature_b64":"4pMkHAKGeD7MuhAZZ4eLLbp6m2uO4HDLEvEfUksZOp2w4RV7EqmPrUct6JyWhzY/hdG4AV0EmeNGq9avHYXFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"197d4318f8eebace50fbb00fc5b2356eca0485333efe18c99680de9f063c548a","last_reissued_at":"2026-07-05T10:30:27.563262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:27.563262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hang Zhou, Hanlin Shang, Hui Li, Jiahao Cui, Jingdong Wang, Kaihui Cheng, Shan Mu, Siyu Zhu, Yun Zhan, Yuqi Ma","submitted_at":"2024-12-01T08:54:30Z","abstract_excerpt":"Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait, and generating immersive, realistic backgrounds. In this paper, we introduce the first application of a pretrained transformer-based video generative model that demonstrates strong generalization capabilities and generates highly dynamic, realistic videos for portrait animation, effectively addressing these challenges. The adoption of a new video backbone model makes previous U-Net-based methods for identity maintena"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00733","kind":"arxiv","version":4},"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/2412.00733/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":"2412.00733","created_at":"2026-07-05T10:30:27.563346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00733v4","created_at":"2026-07-05T10:30:27.563346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00733","created_at":"2026-07-05T10:30:27.563346+00:00"},{"alias_kind":"pith_short_12","alias_value":"DF6UGGHY525M","created_at":"2026-07-05T10:30:27.563346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DF6UGGHY525M4UH3","created_at":"2026-07-05T10:30:27.563346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DF6UGGHY","created_at":"2026-07-05T10:30:27.563346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11180","citing_title":"Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05896","citing_title":"Resonant Minds: Closed-Loop Social Avatars with Theory of Mind","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23552","citing_title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","ref_index":44,"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":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DF6UGGHY525M4UH3WAH4LMRVN3","json":"https://pith.science/pith/DF6UGGHY525M4UH3WAH4LMRVN3.json","graph_json":"https://pith.science/api/pith-number/DF6UGGHY525M4UH3WAH4LMRVN3/graph.json","events_json":"https://pith.science/api/pith-number/DF6UGGHY525M4UH3WAH4LMRVN3/events.json","paper":"https://pith.science/paper/DF6UGGHY"},"agent_actions":{"view_html":"https://pith.science/pith/DF6UGGHY525M4UH3WAH4LMRVN3","download_json":"https://pith.science/pith/DF6UGGHY525M4UH3WAH4LMRVN3.json","view_paper":"https://pith.science/paper/DF6UGGHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00733&json=true","fetch_graph":"https://pith.science/api/pith-number/DF6UGGHY525M4UH3WAH4LMRVN3/graph.json","fetch_events":"https://pith.science/api/pith-number/DF6UGGHY525M4UH3WAH4LMRVN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DF6UGGHY525M4UH3WAH4LMRVN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DF6UGGHY525M4UH3WAH4LMRVN3/action/storage_attestation","attest_author":"https://pith.science/pith/DF6UGGHY525M4UH3WAH4LMRVN3/action/author_attestation","sign_citation":"https://pith.science/pith/DF6UGGHY525M4UH3WAH4LMRVN3/action/citation_signature","submit_replication":"https://pith.science/pith/DF6UGGHY525M4UH3WAH4LMRVN3/action/replication_record"}},"created_at":"2026-07-05T10:30:27.563346+00:00","updated_at":"2026-07-05T10:30:27.563346+00:00"}