{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IFSNYMKFPOYCU4XI4Y24KSDDTS","short_pith_number":"pith:IFSNYMKF","schema_version":"1.0","canonical_sha256":"4164dc31457bb02a72e8e635c548639c94e7fdf97f148fef02375981ed30c107","source":{"kind":"arxiv","id":"2305.06225","version":2},"attestation_state":"computed","paper":{"title":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dan Xu, Fa-Ting Hong, Li Shen","submitted_at":"2023-05-10T14:58:33Z","abstract_excerpt":"Predominant techniques on talking head generation largely depend on 2D information, including facial appearances and motions from input face images. Nevertheless, dense 3D facial geometry, such as pixel-wise depth, plays a critical role in constructing accurate 3D facial structures and suppressing complex background noises for generation. However, dense 3D annotations for facial videos is prohibitively costly to obtain. In this work, firstly, we present a novel self-supervised method for learning dense 3D facial geometry (ie, depth) from face videos, without requiring camera parameters and 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":"2305.06225","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T14:58:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2491e21ffddddc70054d297a25b7e61bd918e6cb8ece84e2ab4c6aacf800c97","abstract_canon_sha256":"fb2fad272236c5ef28804be091f349435dc860efa3e342f859bf2ff130a52439"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:17.684515Z","signature_b64":"8/uv3cFj/XwTyoFcB+jjgMMMMk5i/Whbp2QEKgsLHTQA8Clrt5nGKVtxime8bBQPcSM/GM8KeqfgLbcOJe3LBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4164dc31457bb02a72e8e635c548639c94e7fdf97f148fef02375981ed30c107","last_reissued_at":"2026-07-05T07:22:17.684036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:17.684036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dan Xu, Fa-Ting Hong, Li Shen","submitted_at":"2023-05-10T14:58:33Z","abstract_excerpt":"Predominant techniques on talking head generation largely depend on 2D information, including facial appearances and motions from input face images. Nevertheless, dense 3D facial geometry, such as pixel-wise depth, plays a critical role in constructing accurate 3D facial structures and suppressing complex background noises for generation. However, dense 3D annotations for facial videos is prohibitively costly to obtain. In this work, firstly, we present a novel self-supervised method for learning dense 3D facial geometry (ie, depth) from face videos, without requiring camera parameters and 3D "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06225","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/2305.06225/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":"2305.06225","created_at":"2026-07-05T07:22:17.684092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06225v2","created_at":"2026-07-05T07:22:17.684092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06225","created_at":"2026-07-05T07:22:17.684092+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFSNYMKFPOYC","created_at":"2026-07-05T07:22:17.684092+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFSNYMKFPOYCU4XI","created_at":"2026-07-05T07:22:17.684092+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFSNYMKF","created_at":"2026-07-05T07:22:17.684092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05092","citing_title":"MoDiT: Learning Highly Consistent 3D Motion Coefficients with Diffusion Transformer for Talking Head Generation","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFSNYMKFPOYCU4XI4Y24KSDDTS","json":"https://pith.science/pith/IFSNYMKFPOYCU4XI4Y24KSDDTS.json","graph_json":"https://pith.science/api/pith-number/IFSNYMKFPOYCU4XI4Y24KSDDTS/graph.json","events_json":"https://pith.science/api/pith-number/IFSNYMKFPOYCU4XI4Y24KSDDTS/events.json","paper":"https://pith.science/paper/IFSNYMKF"},"agent_actions":{"view_html":"https://pith.science/pith/IFSNYMKFPOYCU4XI4Y24KSDDTS","download_json":"https://pith.science/pith/IFSNYMKFPOYCU4XI4Y24KSDDTS.json","view_paper":"https://pith.science/paper/IFSNYMKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06225&json=true","fetch_graph":"https://pith.science/api/pith-number/IFSNYMKFPOYCU4XI4Y24KSDDTS/graph.json","fetch_events":"https://pith.science/api/pith-number/IFSNYMKFPOYCU4XI4Y24KSDDTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFSNYMKFPOYCU4XI4Y24KSDDTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFSNYMKFPOYCU4XI4Y24KSDDTS/action/storage_attestation","attest_author":"https://pith.science/pith/IFSNYMKFPOYCU4XI4Y24KSDDTS/action/author_attestation","sign_citation":"https://pith.science/pith/IFSNYMKFPOYCU4XI4Y24KSDDTS/action/citation_signature","submit_replication":"https://pith.science/pith/IFSNYMKFPOYCU4XI4Y24KSDDTS/action/replication_record"}},"created_at":"2026-07-05T07:22:17.684092+00:00","updated_at":"2026-07-05T07:22:17.684092+00:00"}