{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C5UQN7LELGPSYINCQQL3N67TXB","short_pith_number":"pith:C5UQN7LE","schema_version":"1.0","canonical_sha256":"176906fd64599f2c21a28417b6fbf3b85703e1598144029c72cc10ef38454727","source":{"kind":"arxiv","id":"2407.01034","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Corentin Nivelet Etcheberry, Han EunGi, Janghoon Joo, Kim Sung-Bin, Oh Hyun-Bin, Suekyeong Nam, Tae-Hyun Oh","submitted_at":"2024-07-01T07:39:28Z","abstract_excerpt":"Speech-driven 3D facial animation has recently garnered attention due to its cost-effective usability in multimedia production. However, most current advances overlook the intelligibility of lip movements, limiting the realism of facial expressions. In this paper, we introduce a method for speech-driven 3D facial animation to generate accurate lip movements, proposing an audio-visual multimodal perceptual loss. This loss provides guidance to train the speech-driven 3D facial animators to generate plausible lip motions aligned with the spoken transcripts. Furthermore, to incorporate the propose"},"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":"2407.01034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T07:39:28Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"551d35a68187ea84dcb8192dba10233dd1292d34c468ab17e85ad8db226ea3e0","abstract_canon_sha256":"efdd7059671dd45392e0cc51ca8b780ad854ef30cf4a787a9e14b7c72cb41153"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:42.040083Z","signature_b64":"IHDW50u3BNJuTcvpLDxuPl0lwCiJI+Bhmm/ukA9J18RLtGZdlBXQdpyTNbfj+Tnk81EvR9R6pvQx5ifOD97UDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"176906fd64599f2c21a28417b6fbf3b85703e1598144029c72cc10ef38454727","last_reissued_at":"2026-07-05T08:38:42.039653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:42.039653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Corentin Nivelet Etcheberry, Han EunGi, Janghoon Joo, Kim Sung-Bin, Oh Hyun-Bin, Suekyeong Nam, Tae-Hyun Oh","submitted_at":"2024-07-01T07:39:28Z","abstract_excerpt":"Speech-driven 3D facial animation has recently garnered attention due to its cost-effective usability in multimedia production. However, most current advances overlook the intelligibility of lip movements, limiting the realism of facial expressions. In this paper, we introduce a method for speech-driven 3D facial animation to generate accurate lip movements, proposing an audio-visual multimodal perceptual loss. This loss provides guidance to train the speech-driven 3D facial animators to generate plausible lip motions aligned with the spoken transcripts. Furthermore, to incorporate the propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01034","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/2407.01034/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":"2407.01034","created_at":"2026-07-05T08:38:42.039710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01034v1","created_at":"2026-07-05T08:38:42.039710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01034","created_at":"2026-07-05T08:38:42.039710+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5UQN7LELGPS","created_at":"2026-07-05T08:38:42.039710+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5UQN7LELGPSYINC","created_at":"2026-07-05T08:38:42.039710+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5UQN7LE","created_at":"2026-07-05T08:38:42.039710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06060","citing_title":"VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5UQN7LELGPSYINCQQL3N67TXB","json":"https://pith.science/pith/C5UQN7LELGPSYINCQQL3N67TXB.json","graph_json":"https://pith.science/api/pith-number/C5UQN7LELGPSYINCQQL3N67TXB/graph.json","events_json":"https://pith.science/api/pith-number/C5UQN7LELGPSYINCQQL3N67TXB/events.json","paper":"https://pith.science/paper/C5UQN7LE"},"agent_actions":{"view_html":"https://pith.science/pith/C5UQN7LELGPSYINCQQL3N67TXB","download_json":"https://pith.science/pith/C5UQN7LELGPSYINCQQL3N67TXB.json","view_paper":"https://pith.science/paper/C5UQN7LE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01034&json=true","fetch_graph":"https://pith.science/api/pith-number/C5UQN7LELGPSYINCQQL3N67TXB/graph.json","fetch_events":"https://pith.science/api/pith-number/C5UQN7LELGPSYINCQQL3N67TXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5UQN7LELGPSYINCQQL3N67TXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5UQN7LELGPSYINCQQL3N67TXB/action/storage_attestation","attest_author":"https://pith.science/pith/C5UQN7LELGPSYINCQQL3N67TXB/action/author_attestation","sign_citation":"https://pith.science/pith/C5UQN7LELGPSYINCQQL3N67TXB/action/citation_signature","submit_replication":"https://pith.science/pith/C5UQN7LELGPSYINCQQL3N67TXB/action/replication_record"}},"created_at":"2026-07-05T08:38:42.039710+00:00","updated_at":"2026-07-05T08:38:42.039710+00:00"}