{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B4BKXC7DAJ3XK2BH2NIC3CBWZ2","short_pith_number":"pith:B4BKXC7D","schema_version":"1.0","canonical_sha256":"0f02ab8be30277756827d3502d8836ceaebcf934e353de78f90d532cefc9d864","source":{"kind":"arxiv","id":"2504.19165","version":2},"attestation_state":"computed","paper":{"title":"IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feitong Tan, Sean Fanello, Yinda Zhang, Yuan Li, Zhaopeng Cui, Ziqian Bai","submitted_at":"2025-04-27T08:56:02Z","abstract_excerpt":"We propose a novel 3D-aware diffusion-based method for generating photorealistic talking head videos directly from a single identity image and explicit control signals (e.g., expressions). Our method generates Multiplane Images (MPIs) that ensure geometric consistency, making them ideal for immersive viewing experiences like binocular videos for VR headsets. Unlike existing methods that often require a separate stage or joint optimization to reconstruct a 3D representation (such as NeRF or 3D Gaussians), our approach directly generates the final output through a single denoising process, elimi"},"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":"2504.19165","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-27T08:56:02Z","cross_cats_sorted":[],"title_canon_sha256":"fb0762cf18f15cd48a0ce5957e6228cdac439fac8f1042040cdcd4dbf6190de7","abstract_canon_sha256":"6c56e3cb065241f537518d2828da30566c26fe3de9b61ff37a4f451e79523072"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:35.460791Z","signature_b64":"1/iNas3/wrsqPdkuX3Nzo+EchJDGnmXcEYM7d6J+iA7FUJRLJqj1mvMeA6CG7DxOfLnz5Gn4VzIeNfN1j+KlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f02ab8be30277756827d3502d8836ceaebcf934e353de78f90d532cefc9d864","last_reissued_at":"2026-07-05T10:55:35.460307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:35.460307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feitong Tan, Sean Fanello, Yinda Zhang, Yuan Li, Zhaopeng Cui, Ziqian Bai","submitted_at":"2025-04-27T08:56:02Z","abstract_excerpt":"We propose a novel 3D-aware diffusion-based method for generating photorealistic talking head videos directly from a single identity image and explicit control signals (e.g., expressions). Our method generates Multiplane Images (MPIs) that ensure geometric consistency, making them ideal for immersive viewing experiences like binocular videos for VR headsets. Unlike existing methods that often require a separate stage or joint optimization to reconstruct a 3D representation (such as NeRF or 3D Gaussians), our approach directly generates the final output through a single denoising process, elimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19165","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/2504.19165/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":"2504.19165","created_at":"2026-07-05T10:55:35.460370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.19165v2","created_at":"2026-07-05T10:55:35.460370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19165","created_at":"2026-07-05T10:55:35.460370+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4BKXC7DAJ3X","created_at":"2026-07-05T10:55:35.460370+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4BKXC7DAJ3XK2BH","created_at":"2026-07-05T10:55:35.460370+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4BKXC7D","created_at":"2026-07-05T10:55:35.460370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4BKXC7DAJ3XK2BH2NIC3CBWZ2","json":"https://pith.science/pith/B4BKXC7DAJ3XK2BH2NIC3CBWZ2.json","graph_json":"https://pith.science/api/pith-number/B4BKXC7DAJ3XK2BH2NIC3CBWZ2/graph.json","events_json":"https://pith.science/api/pith-number/B4BKXC7DAJ3XK2BH2NIC3CBWZ2/events.json","paper":"https://pith.science/paper/B4BKXC7D"},"agent_actions":{"view_html":"https://pith.science/pith/B4BKXC7DAJ3XK2BH2NIC3CBWZ2","download_json":"https://pith.science/pith/B4BKXC7DAJ3XK2BH2NIC3CBWZ2.json","view_paper":"https://pith.science/paper/B4BKXC7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.19165&json=true","fetch_graph":"https://pith.science/api/pith-number/B4BKXC7DAJ3XK2BH2NIC3CBWZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/B4BKXC7DAJ3XK2BH2NIC3CBWZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4BKXC7DAJ3XK2BH2NIC3CBWZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4BKXC7DAJ3XK2BH2NIC3CBWZ2/action/storage_attestation","attest_author":"https://pith.science/pith/B4BKXC7DAJ3XK2BH2NIC3CBWZ2/action/author_attestation","sign_citation":"https://pith.science/pith/B4BKXC7DAJ3XK2BH2NIC3CBWZ2/action/citation_signature","submit_replication":"https://pith.science/pith/B4BKXC7DAJ3XK2BH2NIC3CBWZ2/action/replication_record"}},"created_at":"2026-07-05T10:55:35.460370+00:00","updated_at":"2026-07-05T10:55:35.460370+00:00"}