{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BUNYYZNNDVTRCIOUYGMTKNMA6M","short_pith_number":"pith:BUNYYZNN","schema_version":"1.0","canonical_sha256":"0d1b8c65ad1d671121d4c199353580f32c920d5591dd302a3e1b6ea57c0de001","source":{"kind":"arxiv","id":"2303.03988","version":1},"attestation_state":"computed","paper":{"title":"DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjie Fan, Tangjie Lv, Wenjin Deng, Yu Ding, Zhimeng Zhang, Zhipeng Hu","submitted_at":"2023-03-07T15:39:54Z","abstract_excerpt":"For few-shot learning, it is still a critical challenge to realize photo-realistic face visually dubbing on high-resolution videos. Previous works fail to generate high-fidelity dubbing results. To address the above problem, this paper proposes a Deformation Inpainting Network (DINet) for high-resolution face visually dubbing. Different from previous works relying on multiple up-sample layers to directly generate pixels from latent embeddings, DINet performs spatial deformation on feature maps of reference images to better preserve high-frequency textural details. Specifically, DINet consists "},"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":"2303.03988","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-07T15:39:54Z","cross_cats_sorted":[],"title_canon_sha256":"6b4c9adea3a5da1fb4ad7c75ccbd1ffb5e1efd8eeb40c8340ddcebb2f81d6f96","abstract_canon_sha256":"3146fd5d78a9d6d7f91054391902580314b0c972bde7b57fec0a8ecb1c9ecf66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:01.990365Z","signature_b64":"HEoboZ1ckRbd1qTNiuYDL+NvhZzQbFq1jis2L1nF6y+puSci4OHkeuPNyQfEcxT8WmjcILaLJ6xYoNnmtIhxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d1b8c65ad1d671121d4c199353580f32c920d5591dd302a3e1b6ea57c0de001","last_reissued_at":"2026-07-05T05:49:01.990012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:01.990012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjie Fan, Tangjie Lv, Wenjin Deng, Yu Ding, Zhimeng Zhang, Zhipeng Hu","submitted_at":"2023-03-07T15:39:54Z","abstract_excerpt":"For few-shot learning, it is still a critical challenge to realize photo-realistic face visually dubbing on high-resolution videos. Previous works fail to generate high-fidelity dubbing results. To address the above problem, this paper proposes a Deformation Inpainting Network (DINet) for high-resolution face visually dubbing. Different from previous works relying on multiple up-sample layers to directly generate pixels from latent embeddings, DINet performs spatial deformation on feature maps of reference images to better preserve high-frequency textural details. Specifically, DINet consists "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03988","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/2303.03988/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":"2303.03988","created_at":"2026-07-05T05:49:01.990068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03988v1","created_at":"2026-07-05T05:49:01.990068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03988","created_at":"2026-07-05T05:49:01.990068+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUNYYZNNDVTR","created_at":"2026-07-05T05:49:01.990068+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUNYYZNNDVTRCIOU","created_at":"2026-07-05T05:49:01.990068+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUNYYZNN","created_at":"2026-07-05T05:49:01.990068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23343","citing_title":"Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUNYYZNNDVTRCIOUYGMTKNMA6M","json":"https://pith.science/pith/BUNYYZNNDVTRCIOUYGMTKNMA6M.json","graph_json":"https://pith.science/api/pith-number/BUNYYZNNDVTRCIOUYGMTKNMA6M/graph.json","events_json":"https://pith.science/api/pith-number/BUNYYZNNDVTRCIOUYGMTKNMA6M/events.json","paper":"https://pith.science/paper/BUNYYZNN"},"agent_actions":{"view_html":"https://pith.science/pith/BUNYYZNNDVTRCIOUYGMTKNMA6M","download_json":"https://pith.science/pith/BUNYYZNNDVTRCIOUYGMTKNMA6M.json","view_paper":"https://pith.science/paper/BUNYYZNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03988&json=true","fetch_graph":"https://pith.science/api/pith-number/BUNYYZNNDVTRCIOUYGMTKNMA6M/graph.json","fetch_events":"https://pith.science/api/pith-number/BUNYYZNNDVTRCIOUYGMTKNMA6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUNYYZNNDVTRCIOUYGMTKNMA6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUNYYZNNDVTRCIOUYGMTKNMA6M/action/storage_attestation","attest_author":"https://pith.science/pith/BUNYYZNNDVTRCIOUYGMTKNMA6M/action/author_attestation","sign_citation":"https://pith.science/pith/BUNYYZNNDVTRCIOUYGMTKNMA6M/action/citation_signature","submit_replication":"https://pith.science/pith/BUNYYZNNDVTRCIOUYGMTKNMA6M/action/replication_record"}},"created_at":"2026-07-05T05:49:01.990068+00:00","updated_at":"2026-07-05T05:49:01.990068+00:00"}