{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RT7TW4WRRK24QCDUQRNEZRQSSA","short_pith_number":"pith:RT7TW4WR","schema_version":"1.0","canonical_sha256":"8cff3b72d18ab5c80874845a4cc612901930dbe41d8af3d84c14380a7d5c7392","source":{"kind":"arxiv","id":"2411.16199","version":6},"attestation_state":"computed","paper":{"title":"VIRES: Video Instance Repainting via Sketch and Text Guided Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxin Shi, Han Jiang, Haojie Zheng, Peixuan Zhang, Shuchen Weng, Si Li, Yuchen Hong","submitted_at":"2024-11-25T08:55:41Z","abstract_excerpt":"We introduce VIRES, a video instance repainting method with sketch and text guidance, enabling video instance repainting, replacement, generation, and removal. Existing approaches struggle with temporal consistency and accurate alignment with the provided sketch sequence. VIRES leverages the generative priors of text-to-video models to maintain temporal consistency and produce visually pleasing results. We propose the Sequential ControlNet with the standardized self-scaling, which effectively extracts structure layouts and adaptively captures high-contrast sketch details. We further augment th"},"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":"2411.16199","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T08:55:41Z","cross_cats_sorted":[],"title_canon_sha256":"2fba84b82550a51559961b639dc99eafb42c8f8d8b4597e5cd2601b9c81ca733","abstract_canon_sha256":"5076f9c7e48cb0e73af140ece6cf2527c5aa9f9e9dac38698f78a9fcefdb505b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:57.311307Z","signature_b64":"N8pCtj7gxY/8hAWjMctV8DhBqAT3UUCeAagXnWFllKXyXMckXWUOZ9hgyd1XdzMsJh2Ux7c0QHs/09A01O1QAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cff3b72d18ab5c80874845a4cc612901930dbe41d8af3d84c14380a7d5c7392","last_reissued_at":"2026-07-05T10:45:57.310823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:57.310823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIRES: Video Instance Repainting via Sketch and Text Guided Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxin Shi, Han Jiang, Haojie Zheng, Peixuan Zhang, Shuchen Weng, Si Li, Yuchen Hong","submitted_at":"2024-11-25T08:55:41Z","abstract_excerpt":"We introduce VIRES, a video instance repainting method with sketch and text guidance, enabling video instance repainting, replacement, generation, and removal. Existing approaches struggle with temporal consistency and accurate alignment with the provided sketch sequence. VIRES leverages the generative priors of text-to-video models to maintain temporal consistency and produce visually pleasing results. We propose the Sequential ControlNet with the standardized self-scaling, which effectively extracts structure layouts and adaptively captures high-contrast sketch details. We further augment th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16199","kind":"arxiv","version":6},"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/2411.16199/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":"2411.16199","created_at":"2026-07-05T10:45:57.310897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16199v6","created_at":"2026-07-05T10:45:57.310897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16199","created_at":"2026-07-05T10:45:57.310897+00:00"},{"alias_kind":"pith_short_12","alias_value":"RT7TW4WRRK24","created_at":"2026-07-05T10:45:57.310897+00:00"},{"alias_kind":"pith_short_16","alias_value":"RT7TW4WRRK24QCDU","created_at":"2026-07-05T10:45:57.310897+00:00"},{"alias_kind":"pith_short_8","alias_value":"RT7TW4WR","created_at":"2026-07-05T10:45:57.310897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24336","citing_title":"TIGER: Taming Identity, Geometry, and Generative Priors for High-Quality Face Video Restoration","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24336","citing_title":"TIGER: Taming Identity, Geometry, and Generative Priors for High-Quality Face Video Restoration","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23709","citing_title":"Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RT7TW4WRRK24QCDUQRNEZRQSSA","json":"https://pith.science/pith/RT7TW4WRRK24QCDUQRNEZRQSSA.json","graph_json":"https://pith.science/api/pith-number/RT7TW4WRRK24QCDUQRNEZRQSSA/graph.json","events_json":"https://pith.science/api/pith-number/RT7TW4WRRK24QCDUQRNEZRQSSA/events.json","paper":"https://pith.science/paper/RT7TW4WR"},"agent_actions":{"view_html":"https://pith.science/pith/RT7TW4WRRK24QCDUQRNEZRQSSA","download_json":"https://pith.science/pith/RT7TW4WRRK24QCDUQRNEZRQSSA.json","view_paper":"https://pith.science/paper/RT7TW4WR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16199&json=true","fetch_graph":"https://pith.science/api/pith-number/RT7TW4WRRK24QCDUQRNEZRQSSA/graph.json","fetch_events":"https://pith.science/api/pith-number/RT7TW4WRRK24QCDUQRNEZRQSSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RT7TW4WRRK24QCDUQRNEZRQSSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RT7TW4WRRK24QCDUQRNEZRQSSA/action/storage_attestation","attest_author":"https://pith.science/pith/RT7TW4WRRK24QCDUQRNEZRQSSA/action/author_attestation","sign_citation":"https://pith.science/pith/RT7TW4WRRK24QCDUQRNEZRQSSA/action/citation_signature","submit_replication":"https://pith.science/pith/RT7TW4WRRK24QCDUQRNEZRQSSA/action/replication_record"}},"created_at":"2026-07-05T10:45:57.310897+00:00","updated_at":"2026-07-05T10:45:57.310897+00:00"}