{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7K6V6HJU2ZCNNBUFVSCUAHEBI4","short_pith_number":"pith:7K6V6HJU","schema_version":"1.0","canonical_sha256":"fabd5f1d34d644d68685ac85401c81471470f717d125c671397d3e1f8af3c0d8","source":{"kind":"arxiv","id":"2501.01427","version":4},"attestation_state":"computed","paper":{"title":"VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Luo, Hengshuang Zhao, Sihui Ji, Xiang Bai, Xi Chen, Yuanpeng Tu","submitted_at":"2025-01-02T18:59:54Z","abstract_excerpt":"Despite significant advancements in video generation, inserting a given object into videos remains a challenging task. The difficulty lies in preserving the appearance details of the reference object and accurately modeling coherent motions at the same time. In this paper, we propose VideoAnydoor, a zero-shot video object insertion framework with high-fidelity detail preservation and precise motion control. Starting from a text-to-video model, we utilize an ID extractor to inject the global identity and leverage a box sequence to control the overall motion. To preserve the detailed appearance "},"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":"2501.01427","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"5bea856c65037e41d48c7c487bd246ba6de7ee3ff0a4d91f3edb1d81b0dff068","abstract_canon_sha256":"fd39e29c5b969bacbf6e1d84f9e3d790d6d2c952a2f3ee44e588561098f0d121"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:50.053010Z","signature_b64":"xzn4FuHTtDq0A94PMkucpEjQMNccKUPKe+e5Tcq+wT6OTBFQquMCGz+qguHN/uC5+IAwrd0OhrboMe5WZsSEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fabd5f1d34d644d68685ac85401c81471470f717d125c671397d3e1f8af3c0d8","last_reissued_at":"2026-07-05T11:10:50.052465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:50.052465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Luo, Hengshuang Zhao, Sihui Ji, Xiang Bai, Xi Chen, Yuanpeng Tu","submitted_at":"2025-01-02T18:59:54Z","abstract_excerpt":"Despite significant advancements in video generation, inserting a given object into videos remains a challenging task. The difficulty lies in preserving the appearance details of the reference object and accurately modeling coherent motions at the same time. In this paper, we propose VideoAnydoor, a zero-shot video object insertion framework with high-fidelity detail preservation and precise motion control. Starting from a text-to-video model, we utilize an ID extractor to inject the global identity and leverage a box sequence to control the overall motion. To preserve the detailed appearance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01427","kind":"arxiv","version":4},"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/2501.01427/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":"2501.01427","created_at":"2026-07-05T11:10:50.052540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01427v4","created_at":"2026-07-05T11:10:50.052540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01427","created_at":"2026-07-05T11:10:50.052540+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K6V6HJU2ZCN","created_at":"2026-07-05T11:10:50.052540+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K6V6HJU2ZCNNBUF","created_at":"2026-07-05T11:10:50.052540+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K6V6HJU","created_at":"2026-07-05T11:10:50.052540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23245","citing_title":"SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04434","citing_title":"Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03637","citing_title":"Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11244","citing_title":"Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7K6V6HJU2ZCNNBUFVSCUAHEBI4","json":"https://pith.science/pith/7K6V6HJU2ZCNNBUFVSCUAHEBI4.json","graph_json":"https://pith.science/api/pith-number/7K6V6HJU2ZCNNBUFVSCUAHEBI4/graph.json","events_json":"https://pith.science/api/pith-number/7K6V6HJU2ZCNNBUFVSCUAHEBI4/events.json","paper":"https://pith.science/paper/7K6V6HJU"},"agent_actions":{"view_html":"https://pith.science/pith/7K6V6HJU2ZCNNBUFVSCUAHEBI4","download_json":"https://pith.science/pith/7K6V6HJU2ZCNNBUFVSCUAHEBI4.json","view_paper":"https://pith.science/paper/7K6V6HJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01427&json=true","fetch_graph":"https://pith.science/api/pith-number/7K6V6HJU2ZCNNBUFVSCUAHEBI4/graph.json","fetch_events":"https://pith.science/api/pith-number/7K6V6HJU2ZCNNBUFVSCUAHEBI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K6V6HJU2ZCNNBUFVSCUAHEBI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K6V6HJU2ZCNNBUFVSCUAHEBI4/action/storage_attestation","attest_author":"https://pith.science/pith/7K6V6HJU2ZCNNBUFVSCUAHEBI4/action/author_attestation","sign_citation":"https://pith.science/pith/7K6V6HJU2ZCNNBUFVSCUAHEBI4/action/citation_signature","submit_replication":"https://pith.science/pith/7K6V6HJU2ZCNNBUFVSCUAHEBI4/action/replication_record"}},"created_at":"2026-07-05T11:10:50.052540+00:00","updated_at":"2026-07-05T11:10:50.052540+00:00"}