{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PJ52KGNKM6ZAAQSECUNK2TSMGT","short_pith_number":"pith:PJ52KGNK","schema_version":"1.0","canonical_sha256":"7a7ba519aa67b2004244151aad4e4c34cc35f9691767fed0c1966b974376d96e","source":{"kind":"arxiv","id":"2409.19911","version":2},"attestation_state":"computed","paper":{"title":"Replace Anyone in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Chunhua Shen, Haonan Qiu, Nong Sang, Ruihang Chu, Shiwei Zhang, Xiang Wang, Yingya Zhang, Yuehuan Wang, Zekun Li","submitted_at":"2024-09-30T03:27:33Z","abstract_excerpt":"The field of controllable human-centric video generation has witnessed remarkable progress, particularly with the advent of diffusion models. However, achieving precise and localized control over human motion in videos, such as replacing or inserting individuals while preserving desired motion patterns, still remains a formidable challenge. In this work, we present the ReplaceAnyone framework, which focuses on localized human replacement and insertion featuring intricate backgrounds. Specifically, we formulate this task as an image-conditioned video inpainting paradigm with pose guidance, util"},"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":"2409.19911","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T03:27:33Z","cross_cats_sorted":[],"title_canon_sha256":"1876f55b75a4fe98aa7a1618595464eda2d82f52ffd952ad23930271dc274255","abstract_canon_sha256":"29af01f1145edf5a204a17945ea08be185064b5d27ce47a2ec6b9d62e2aff425"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:25.049225Z","signature_b64":"Tf1RcW7iAiCEyWrpj9D6vzgHsp0uNvIBUU5wWqkPBuQJH2PfKNMuzMwUprF8EqrQGZJqBMDNLjZBY8sWk6rOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a7ba519aa67b2004244151aad4e4c34cc35f9691767fed0c1966b974376d96e","last_reissued_at":"2026-07-05T10:59:25.048694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:25.048694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Replace Anyone in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Chunhua Shen, Haonan Qiu, Nong Sang, Ruihang Chu, Shiwei Zhang, Xiang Wang, Yingya Zhang, Yuehuan Wang, Zekun Li","submitted_at":"2024-09-30T03:27:33Z","abstract_excerpt":"The field of controllable human-centric video generation has witnessed remarkable progress, particularly with the advent of diffusion models. However, achieving precise and localized control over human motion in videos, such as replacing or inserting individuals while preserving desired motion patterns, still remains a formidable challenge. In this work, we present the ReplaceAnyone framework, which focuses on localized human replacement and insertion featuring intricate backgrounds. Specifically, we formulate this task as an image-conditioned video inpainting paradigm with pose guidance, util"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19911","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/2409.19911/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":"2409.19911","created_at":"2026-07-05T10:59:25.048758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19911v2","created_at":"2026-07-05T10:59:25.048758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19911","created_at":"2026-07-05T10:59:25.048758+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJ52KGNKM6ZA","created_at":"2026-07-05T10:59:25.048758+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJ52KGNKM6ZAAQSE","created_at":"2026-07-05T10:59:25.048758+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJ52KGNK","created_at":"2026-07-05T10:59:25.048758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.11755","citing_title":"Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19720","citing_title":"ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJ52KGNKM6ZAAQSECUNK2TSMGT","json":"https://pith.science/pith/PJ52KGNKM6ZAAQSECUNK2TSMGT.json","graph_json":"https://pith.science/api/pith-number/PJ52KGNKM6ZAAQSECUNK2TSMGT/graph.json","events_json":"https://pith.science/api/pith-number/PJ52KGNKM6ZAAQSECUNK2TSMGT/events.json","paper":"https://pith.science/paper/PJ52KGNK"},"agent_actions":{"view_html":"https://pith.science/pith/PJ52KGNKM6ZAAQSECUNK2TSMGT","download_json":"https://pith.science/pith/PJ52KGNKM6ZAAQSECUNK2TSMGT.json","view_paper":"https://pith.science/paper/PJ52KGNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19911&json=true","fetch_graph":"https://pith.science/api/pith-number/PJ52KGNKM6ZAAQSECUNK2TSMGT/graph.json","fetch_events":"https://pith.science/api/pith-number/PJ52KGNKM6ZAAQSECUNK2TSMGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJ52KGNKM6ZAAQSECUNK2TSMGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJ52KGNKM6ZAAQSECUNK2TSMGT/action/storage_attestation","attest_author":"https://pith.science/pith/PJ52KGNKM6ZAAQSECUNK2TSMGT/action/author_attestation","sign_citation":"https://pith.science/pith/PJ52KGNKM6ZAAQSECUNK2TSMGT/action/citation_signature","submit_replication":"https://pith.science/pith/PJ52KGNKM6ZAAQSECUNK2TSMGT/action/replication_record"}},"created_at":"2026-07-05T10:59:25.048758+00:00","updated_at":"2026-07-05T10:59:25.048758+00:00"}