{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LHV3HIX2YSHQIUH2BDNIIOTCVC","short_pith_number":"pith:LHV3HIX2","schema_version":"1.0","canonical_sha256":"59ebb3a2fac48f0450fa08da843a62a8b383494ae02ab9227990f5c46ca0b164","source":{"kind":"arxiv","id":"2301.13173","version":1},"attestation_state":"computed","paper":{"title":"Shape-aware Text-driven Layered Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Elizabeth Qiu, Jia-Bin Huang, Ji-Ze Genevieve Jang, Yao-Chih Lee, Yi-Ting Chen","submitted_at":"2023-01-30T18:41:58Z","abstract_excerpt":"Temporal consistency is essential for video editing applications. Existing work on layered representation of videos allows propagating edits consistently to each frame. These methods, however, can only edit object appearance rather than object shape changes due to the limitation of using a fixed UV mapping field for texture atlas. We present a shape-aware, text-driven video editing method to tackle this challenge. To handle shape changes in video editing, we first propagate the deformation field between the input and edited keyframe to all frames. We then leverage a pre-trained text-conditione"},"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":"2301.13173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-30T18:41:58Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"1c60321c2b3e65e8c46a744ec566f439204b71ab3157cf0c2179e156ab8b0d3a","abstract_canon_sha256":"dd1fdff9b970757abfe6aaada12c5ed83f9d17709fcb868ee19eb2b72bbec9e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:01.484051Z","signature_b64":"DxyC3ukfOquCfBTJxa54pW4E/mfyq3uF6VQ9WMZy310G8/1VBOGQ1WhyaMfCxFcGPINNHVdCt++SJ4Fpe5trAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59ebb3a2fac48f0450fa08da843a62a8b383494ae02ab9227990f5c46ca0b164","last_reissued_at":"2026-07-05T05:37:01.483621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:01.483621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shape-aware Text-driven Layered Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Elizabeth Qiu, Jia-Bin Huang, Ji-Ze Genevieve Jang, Yao-Chih Lee, Yi-Ting Chen","submitted_at":"2023-01-30T18:41:58Z","abstract_excerpt":"Temporal consistency is essential for video editing applications. Existing work on layered representation of videos allows propagating edits consistently to each frame. These methods, however, can only edit object appearance rather than object shape changes due to the limitation of using a fixed UV mapping field for texture atlas. We present a shape-aware, text-driven video editing method to tackle this challenge. To handle shape changes in video editing, we first propagate the deformation field between the input and edited keyframe to all frames. We then leverage a pre-trained text-conditione"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13173","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/2301.13173/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":"2301.13173","created_at":"2026-07-05T05:37:01.483673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13173v1","created_at":"2026-07-05T05:37:01.483673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13173","created_at":"2026-07-05T05:37:01.483673+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHV3HIX2YSHQ","created_at":"2026-07-05T05:37:01.483673+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHV3HIX2YSHQIUH2","created_at":"2026-07-05T05:37:01.483673+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHV3HIX2","created_at":"2026-07-05T05:37:01.483673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2307.10373","citing_title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHV3HIX2YSHQIUH2BDNIIOTCVC","json":"https://pith.science/pith/LHV3HIX2YSHQIUH2BDNIIOTCVC.json","graph_json":"https://pith.science/api/pith-number/LHV3HIX2YSHQIUH2BDNIIOTCVC/graph.json","events_json":"https://pith.science/api/pith-number/LHV3HIX2YSHQIUH2BDNIIOTCVC/events.json","paper":"https://pith.science/paper/LHV3HIX2"},"agent_actions":{"view_html":"https://pith.science/pith/LHV3HIX2YSHQIUH2BDNIIOTCVC","download_json":"https://pith.science/pith/LHV3HIX2YSHQIUH2BDNIIOTCVC.json","view_paper":"https://pith.science/paper/LHV3HIX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13173&json=true","fetch_graph":"https://pith.science/api/pith-number/LHV3HIX2YSHQIUH2BDNIIOTCVC/graph.json","fetch_events":"https://pith.science/api/pith-number/LHV3HIX2YSHQIUH2BDNIIOTCVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHV3HIX2YSHQIUH2BDNIIOTCVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHV3HIX2YSHQIUH2BDNIIOTCVC/action/storage_attestation","attest_author":"https://pith.science/pith/LHV3HIX2YSHQIUH2BDNIIOTCVC/action/author_attestation","sign_citation":"https://pith.science/pith/LHV3HIX2YSHQIUH2BDNIIOTCVC/action/citation_signature","submit_replication":"https://pith.science/pith/LHV3HIX2YSHQIUH2BDNIIOTCVC/action/replication_record"}},"created_at":"2026-07-05T05:37:01.483673+00:00","updated_at":"2026-07-05T05:37:01.483673+00:00"}