{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T7SHUYYXC5YOJC2JBU2Z7YIIMK","short_pith_number":"pith:T7SHUYYX","schema_version":"1.0","canonical_sha256":"9fe47a63171770e48b490d359fe108629850f4d7853878b930577c630fbc7a8a","source":{"kind":"arxiv","id":"2504.03041","version":1},"attestation_state":"computed","paper":{"title":"VIP: Video Inpainting Pipeline for Real World Human Removal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chiuman Ho, Daitao Xing, Huiming Sun, Jiaming Ding, Jiang Geng, Jie Cai, Kaiyu Zhang, Kangning Yang, Lan Fu, Ming Chen, Ruineng Li, Yangbo Xie, Yikang Li, Zibo Meng","submitted_at":"2025-04-03T21:40:10Z","abstract_excerpt":"Inpainting for real-world human and pedestrian removal in high-resolution video clips presents significant challenges, particularly in achieving high-quality outcomes, ensuring temporal consistency, and managing complex object interactions that involve humans, their belongings, and their shadows. In this paper, we introduce VIP (Video Inpainting Pipeline), a novel promptless video inpainting framework for real-world human removal applications. VIP enhances a state-of-the-art text-to-video model with a motion module and employs a Variational Autoencoder (VAE) for progressive denoising in the la"},"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":"2504.03041","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T21:40:10Z","cross_cats_sorted":[],"title_canon_sha256":"72ac6bc38f7155daaa6936e692b148f086d8e228042f984fd975ac3e8280f15c","abstract_canon_sha256":"aafa51a7d181b8d8123176dd403513e09d3a0395034bb77c91431e97f8eb6269"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:25.243777Z","signature_b64":"m+HimXiIXly/wcB3VFrgDm4bJ7Wm65uyBvDb9gzluzyqcRE4bIDu8r/lzXVRN2mGTtd4/8cDeybOMEYd3uinDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fe47a63171770e48b490d359fe108629850f4d7853878b930577c630fbc7a8a","last_reissued_at":"2026-07-05T10:44:25.243160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:25.243160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIP: Video Inpainting Pipeline for Real World Human Removal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chiuman Ho, Daitao Xing, Huiming Sun, Jiaming Ding, Jiang Geng, Jie Cai, Kaiyu Zhang, Kangning Yang, Lan Fu, Ming Chen, Ruineng Li, Yangbo Xie, Yikang Li, Zibo Meng","submitted_at":"2025-04-03T21:40:10Z","abstract_excerpt":"Inpainting for real-world human and pedestrian removal in high-resolution video clips presents significant challenges, particularly in achieving high-quality outcomes, ensuring temporal consistency, and managing complex object interactions that involve humans, their belongings, and their shadows. In this paper, we introduce VIP (Video Inpainting Pipeline), a novel promptless video inpainting framework for real-world human removal applications. VIP enhances a state-of-the-art text-to-video model with a motion module and employs a Variational Autoencoder (VAE) for progressive denoising in the la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03041","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/2504.03041/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":"2504.03041","created_at":"2026-07-05T10:44:25.243226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03041v1","created_at":"2026-07-05T10:44:25.243226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03041","created_at":"2026-07-05T10:44:25.243226+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7SHUYYXC5YO","created_at":"2026-07-05T10:44:25.243226+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7SHUYYXC5YOJC2J","created_at":"2026-07-05T10:44:25.243226+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7SHUYYX","created_at":"2026-07-05T10:44:25.243226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.21901","citing_title":"CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T7SHUYYXC5YOJC2JBU2Z7YIIMK","json":"https://pith.science/pith/T7SHUYYXC5YOJC2JBU2Z7YIIMK.json","graph_json":"https://pith.science/api/pith-number/T7SHUYYXC5YOJC2JBU2Z7YIIMK/graph.json","events_json":"https://pith.science/api/pith-number/T7SHUYYXC5YOJC2JBU2Z7YIIMK/events.json","paper":"https://pith.science/paper/T7SHUYYX"},"agent_actions":{"view_html":"https://pith.science/pith/T7SHUYYXC5YOJC2JBU2Z7YIIMK","download_json":"https://pith.science/pith/T7SHUYYXC5YOJC2JBU2Z7YIIMK.json","view_paper":"https://pith.science/paper/T7SHUYYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03041&json=true","fetch_graph":"https://pith.science/api/pith-number/T7SHUYYXC5YOJC2JBU2Z7YIIMK/graph.json","fetch_events":"https://pith.science/api/pith-number/T7SHUYYXC5YOJC2JBU2Z7YIIMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7SHUYYXC5YOJC2JBU2Z7YIIMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7SHUYYXC5YOJC2JBU2Z7YIIMK/action/storage_attestation","attest_author":"https://pith.science/pith/T7SHUYYXC5YOJC2JBU2Z7YIIMK/action/author_attestation","sign_citation":"https://pith.science/pith/T7SHUYYXC5YOJC2JBU2Z7YIIMK/action/citation_signature","submit_replication":"https://pith.science/pith/T7SHUYYXC5YOJC2JBU2Z7YIIMK/action/replication_record"}},"created_at":"2026-07-05T10:44:25.243226+00:00","updated_at":"2026-07-05T10:44:25.243226+00:00"}