{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NPX4IMLJ2X7ZYZCX56O6Q4QONZ","short_pith_number":"pith:NPX4IMLJ","schema_version":"1.0","canonical_sha256":"6befc43169d5ff9c6457ef9de8720e6e75b51f4a82e920daeb99cda23b8eada7","source":{"kind":"arxiv","id":"2401.17509","version":1},"attestation_state":"computed","paper":{"title":"Anything in Any Scene: Photorealistic Video Object Insertion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Bai, Cheng Lu, Chengzhang Zhong, Di Liang, Guoxiang Zhang, Jie Yang, Tao Wang, Xiaoyin Zheng, Yichen Guan, Yiqiao Qiu, Yujian Guo, Zeman Shao, Zhendong Wang, Zhuorui Zhang","submitted_at":"2024-01-30T23:54:43Z","abstract_excerpt":"Realistic video simulation has shown significant potential across diverse applications, from virtual reality to film production. This is particularly true for scenarios where capturing videos in real-world settings is either impractical or expensive. Existing approaches in video simulation often fail to accurately model the lighting environment, represent the object geometry, or achieve high levels of photorealism. In this paper, we propose Anything in Any Scene, a novel and generic framework for realistic video simulation that seamlessly inserts any object into an existing dynamic video with "},"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":"2401.17509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-30T23:54:43Z","cross_cats_sorted":[],"title_canon_sha256":"951102f305ad35a7d7a1251e1bbc0ad28769ae2c767e6fbda38c4fbf255db42d","abstract_canon_sha256":"e3121a11cc2d233439c37ba154acf65bc21bf569095b4e30d3f8b4eed0220e8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:37.956292Z","signature_b64":"EJ1hj+nd6bTeIGBVvs8WVG/Mz79LVXmk6BRDnN9x+wiVB77bTdnToEQ1NJulFvjD1Aw2TCJOBoM0EvaKSMn2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6befc43169d5ff9c6457ef9de8720e6e75b51f4a82e920daeb99cda23b8eada7","last_reissued_at":"2026-07-05T07:39:37.955840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:37.955840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anything in Any Scene: Photorealistic Video Object Insertion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Bai, Cheng Lu, Chengzhang Zhong, Di Liang, Guoxiang Zhang, Jie Yang, Tao Wang, Xiaoyin Zheng, Yichen Guan, Yiqiao Qiu, Yujian Guo, Zeman Shao, Zhendong Wang, Zhuorui Zhang","submitted_at":"2024-01-30T23:54:43Z","abstract_excerpt":"Realistic video simulation has shown significant potential across diverse applications, from virtual reality to film production. This is particularly true for scenarios where capturing videos in real-world settings is either impractical or expensive. Existing approaches in video simulation often fail to accurately model the lighting environment, represent the object geometry, or achieve high levels of photorealism. In this paper, we propose Anything in Any Scene, a novel and generic framework for realistic video simulation that seamlessly inserts any object into an existing dynamic video with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17509","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/2401.17509/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":"2401.17509","created_at":"2026-07-05T07:39:37.955898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17509v1","created_at":"2026-07-05T07:39:37.955898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17509","created_at":"2026-07-05T07:39:37.955898+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPX4IMLJ2X7Z","created_at":"2026-07-05T07:39:37.955898+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPX4IMLJ2X7ZYZCX","created_at":"2026-07-05T07:39:37.955898+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPX4IMLJ","created_at":"2026-07-05T07:39:37.955898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01362","citing_title":"AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23891","citing_title":"Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14556","citing_title":"Controllable Video Object Insertion via Multi-View Priors","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPX4IMLJ2X7ZYZCX56O6Q4QONZ","json":"https://pith.science/pith/NPX4IMLJ2X7ZYZCX56O6Q4QONZ.json","graph_json":"https://pith.science/api/pith-number/NPX4IMLJ2X7ZYZCX56O6Q4QONZ/graph.json","events_json":"https://pith.science/api/pith-number/NPX4IMLJ2X7ZYZCX56O6Q4QONZ/events.json","paper":"https://pith.science/paper/NPX4IMLJ"},"agent_actions":{"view_html":"https://pith.science/pith/NPX4IMLJ2X7ZYZCX56O6Q4QONZ","download_json":"https://pith.science/pith/NPX4IMLJ2X7ZYZCX56O6Q4QONZ.json","view_paper":"https://pith.science/paper/NPX4IMLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17509&json=true","fetch_graph":"https://pith.science/api/pith-number/NPX4IMLJ2X7ZYZCX56O6Q4QONZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NPX4IMLJ2X7ZYZCX56O6Q4QONZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPX4IMLJ2X7ZYZCX56O6Q4QONZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPX4IMLJ2X7ZYZCX56O6Q4QONZ/action/storage_attestation","attest_author":"https://pith.science/pith/NPX4IMLJ2X7ZYZCX56O6Q4QONZ/action/author_attestation","sign_citation":"https://pith.science/pith/NPX4IMLJ2X7ZYZCX56O6Q4QONZ/action/citation_signature","submit_replication":"https://pith.science/pith/NPX4IMLJ2X7ZYZCX56O6Q4QONZ/action/replication_record"}},"created_at":"2026-07-05T07:39:37.955898+00:00","updated_at":"2026-07-05T07:39:37.955898+00:00"}