{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DK6ASJDFQEV3ZV52RPOMHKCB6H","short_pith_number":"pith:DK6ASJDF","schema_version":"1.0","canonical_sha256":"1abc092465812bbcd7ba8bdcc3a841f1f20e220cc25afe882963f157c0ebdd83","source":{"kind":"arxiv","id":"2507.06060","version":2},"attestation_state":"computed","paper":{"title":"VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexandre Symeonidis-Herzig, \\\"Ozge Mercano\\u{g}lu Sincan, Richard Bowden","submitted_at":"2025-07-08T15:04:17Z","abstract_excerpt":"Realistic, high-fidelity 3D facial animations are crucial for expressive avatar systems in human-computer interaction and accessibility. Although prior methods show promising quality, their reliance on the mesh domain limits their ability to fully leverage the rapid visual innovations seen in 2D computer vision and graphics. We propose VisualSpeaker, a novel method that bridges this gap using photorealistic differentiable rendering, supervised by visual speech recognition, for improved 3D facial animation. Our contribution is a perceptual lip-reading loss, derived by passing photorealistic 3D "},"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":"2507.06060","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T15:04:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aee82a44714b184124d48a582c0a251e60f2598b1c55d69c8da54da445590464","abstract_canon_sha256":"8abb36b6a38ece923ceabf52b5e61149e6ffbb9c44eb2688fdfca24a53374664"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:35.288156Z","signature_b64":"FcuOlZm9YFGtIoa5UZ89RYLF9oKtqZUN73a0aazVn+4Uijt3gb2oKofzbNtC3zucZDe4HIZ6D0+A0GisZkOeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1abc092465812bbcd7ba8bdcc3a841f1f20e220cc25afe882963f157c0ebdd83","last_reissued_at":"2026-07-05T11:40:35.287649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:35.287649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexandre Symeonidis-Herzig, \\\"Ozge Mercano\\u{g}lu Sincan, Richard Bowden","submitted_at":"2025-07-08T15:04:17Z","abstract_excerpt":"Realistic, high-fidelity 3D facial animations are crucial for expressive avatar systems in human-computer interaction and accessibility. Although prior methods show promising quality, their reliance on the mesh domain limits their ability to fully leverage the rapid visual innovations seen in 2D computer vision and graphics. We propose VisualSpeaker, a novel method that bridges this gap using photorealistic differentiable rendering, supervised by visual speech recognition, for improved 3D facial animation. Our contribution is a perceptual lip-reading loss, derived by passing photorealistic 3D "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06060","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/2507.06060/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":"2507.06060","created_at":"2026-07-05T11:40:35.287712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06060v2","created_at":"2026-07-05T11:40:35.287712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06060","created_at":"2026-07-05T11:40:35.287712+00:00"},{"alias_kind":"pith_short_12","alias_value":"DK6ASJDFQEV3","created_at":"2026-07-05T11:40:35.287712+00:00"},{"alias_kind":"pith_short_16","alias_value":"DK6ASJDFQEV3ZV52","created_at":"2026-07-05T11:40:35.287712+00:00"},{"alias_kind":"pith_short_8","alias_value":"DK6ASJDF","created_at":"2026-07-05T11:40:35.287712+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/DK6ASJDFQEV3ZV52RPOMHKCB6H","json":"https://pith.science/pith/DK6ASJDFQEV3ZV52RPOMHKCB6H.json","graph_json":"https://pith.science/api/pith-number/DK6ASJDFQEV3ZV52RPOMHKCB6H/graph.json","events_json":"https://pith.science/api/pith-number/DK6ASJDFQEV3ZV52RPOMHKCB6H/events.json","paper":"https://pith.science/paper/DK6ASJDF"},"agent_actions":{"view_html":"https://pith.science/pith/DK6ASJDFQEV3ZV52RPOMHKCB6H","download_json":"https://pith.science/pith/DK6ASJDFQEV3ZV52RPOMHKCB6H.json","view_paper":"https://pith.science/paper/DK6ASJDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06060&json=true","fetch_graph":"https://pith.science/api/pith-number/DK6ASJDFQEV3ZV52RPOMHKCB6H/graph.json","fetch_events":"https://pith.science/api/pith-number/DK6ASJDFQEV3ZV52RPOMHKCB6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DK6ASJDFQEV3ZV52RPOMHKCB6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DK6ASJDFQEV3ZV52RPOMHKCB6H/action/storage_attestation","attest_author":"https://pith.science/pith/DK6ASJDFQEV3ZV52RPOMHKCB6H/action/author_attestation","sign_citation":"https://pith.science/pith/DK6ASJDFQEV3ZV52RPOMHKCB6H/action/citation_signature","submit_replication":"https://pith.science/pith/DK6ASJDFQEV3ZV52RPOMHKCB6H/action/replication_record"}},"created_at":"2026-07-05T11:40:35.287712+00:00","updated_at":"2026-07-05T11:40:35.287712+00:00"}