{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NPC5LIA5DWH3TN6PXEABSWYCAB","short_pith_number":"pith:NPC5LIA5","schema_version":"1.0","canonical_sha256":"6bc5d5a01d1d8fb9b7cfb900195b02006c2071674aeb8930d91cdd22aa7fe745","source":{"kind":"arxiv","id":"2401.05735","version":3},"attestation_state":"computed","paper":{"title":"Object-Centric Diffusion for Efficient Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adil Karjauv, Amirhossein Habibian, Davide Abati, Fatih Porikli, Kumara Kahatapitiya, Yuki M. Asano","submitted_at":"2024-01-11T08:36:15Z","abstract_excerpt":"Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy memory and computational costs to generate temporally-coherent frames, either in the form of diffusion inversion and/or cross-frame attention. In this paper, we conduct an analysis of such inefficiencies, and suggest simple yet effective modifications that allow significant speed-ups whilst maintaining quality. Moreover, we introduce Object-Centric Diffusion, "},"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":"2401.05735","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T08:36:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ea68591ebb3b12bce85c9d1f5bb8a25e93abb229d47596964dc00468ff5bc678","abstract_canon_sha256":"3c7c027f21d4436d425565ab54915346c81f1962cb125302689a5c157d66b9c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:57.133456Z","signature_b64":"h2aIDrcUVZxpMG0ywHfKXfh491xfK72Vlp9XNhJVHmfH9dUZU+IERL6j9vv9yN+JnCsUeOq0RUd+V36yrORgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bc5d5a01d1d8fb9b7cfb900195b02006c2071674aeb8930d91cdd22aa7fe745","last_reissued_at":"2026-07-05T09:00:57.132970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:57.132970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object-Centric Diffusion for Efficient Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adil Karjauv, Amirhossein Habibian, Davide Abati, Fatih Porikli, Kumara Kahatapitiya, Yuki M. Asano","submitted_at":"2024-01-11T08:36:15Z","abstract_excerpt":"Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy memory and computational costs to generate temporally-coherent frames, either in the form of diffusion inversion and/or cross-frame attention. In this paper, we conduct an analysis of such inefficiencies, and suggest simple yet effective modifications that allow significant speed-ups whilst maintaining quality. Moreover, we introduce Object-Centric Diffusion, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05735","kind":"arxiv","version":3},"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/2401.05735/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":"2401.05735","created_at":"2026-07-05T09:00:57.133027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05735v3","created_at":"2026-07-05T09:00:57.133027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05735","created_at":"2026-07-05T09:00:57.133027+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPC5LIA5DWH3","created_at":"2026-07-05T09:00:57.133027+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPC5LIA5DWH3TN6P","created_at":"2026-07-05T09:00:57.133027+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPC5LIA5","created_at":"2026-07-05T09:00:57.133027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04432","citing_title":"DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPC5LIA5DWH3TN6PXEABSWYCAB","json":"https://pith.science/pith/NPC5LIA5DWH3TN6PXEABSWYCAB.json","graph_json":"https://pith.science/api/pith-number/NPC5LIA5DWH3TN6PXEABSWYCAB/graph.json","events_json":"https://pith.science/api/pith-number/NPC5LIA5DWH3TN6PXEABSWYCAB/events.json","paper":"https://pith.science/paper/NPC5LIA5"},"agent_actions":{"view_html":"https://pith.science/pith/NPC5LIA5DWH3TN6PXEABSWYCAB","download_json":"https://pith.science/pith/NPC5LIA5DWH3TN6PXEABSWYCAB.json","view_paper":"https://pith.science/paper/NPC5LIA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05735&json=true","fetch_graph":"https://pith.science/api/pith-number/NPC5LIA5DWH3TN6PXEABSWYCAB/graph.json","fetch_events":"https://pith.science/api/pith-number/NPC5LIA5DWH3TN6PXEABSWYCAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPC5LIA5DWH3TN6PXEABSWYCAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPC5LIA5DWH3TN6PXEABSWYCAB/action/storage_attestation","attest_author":"https://pith.science/pith/NPC5LIA5DWH3TN6PXEABSWYCAB/action/author_attestation","sign_citation":"https://pith.science/pith/NPC5LIA5DWH3TN6PXEABSWYCAB/action/citation_signature","submit_replication":"https://pith.science/pith/NPC5LIA5DWH3TN6PXEABSWYCAB/action/replication_record"}},"created_at":"2026-07-05T09:00:57.133027+00:00","updated_at":"2026-07-05T09:00:57.133027+00:00"}