{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GIXGDBWAHO7ENVQCV7EC3XEAVW","short_pith_number":"pith:GIXGDBWA","schema_version":"1.0","canonical_sha256":"322e6186c03bbe46d602afc82ddc80ad8481eb442eba1272e6f7937c7525447f","source":{"kind":"arxiv","id":"2412.07721","version":2},"attestation_state":"computed","paper":{"title":"ObjCtrl-2.5D: Training-free Object Control with Camera Poses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Shangchen Zhou, Yushi Lan, Zhouxia Wang","submitted_at":"2024-12-10T18:14:30Z","abstract_excerpt":"This study aims to achieve more precise and versatile object control in image-to-video (I2V) generation. Current methods typically represent the spatial movement of target objects with 2D trajectories, which often fail to capture user intention and frequently produce unnatural results. To enhance control, we present ObjCtrl-2.5D, a training-free object control approach that uses a 3D trajectory, extended from a 2D trajectory with depth information, as a control signal. By modeling object movement as camera movement, ObjCtrl-2.5D represents the 3D trajectory as a sequence of camera poses, enabl"},"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":"2412.07721","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:14:30Z","cross_cats_sorted":[],"title_canon_sha256":"a50d1aaf2001964ac548a293184ac9212794d9b6678c5b727ec0bb43720afe6b","abstract_canon_sha256":"3d5143ee048bc493b1bc282049301eb0bbf683d7ef41fe0355a68491c73e7275"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:25.142480Z","signature_b64":"UfHAP2F3rzBfJJr7Q3q0wG4fi3s8Px5RZoekV4v7Kdp0zKPeb+7IqV6KY09rOF8ISA5GhRVQ8diuNAhqqLFDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"322e6186c03bbe46d602afc82ddc80ad8481eb442eba1272e6f7937c7525447f","last_reissued_at":"2026-07-05T11:26:25.142007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:25.142007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ObjCtrl-2.5D: Training-free Object Control with Camera Poses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Shangchen Zhou, Yushi Lan, Zhouxia Wang","submitted_at":"2024-12-10T18:14:30Z","abstract_excerpt":"This study aims to achieve more precise and versatile object control in image-to-video (I2V) generation. Current methods typically represent the spatial movement of target objects with 2D trajectories, which often fail to capture user intention and frequently produce unnatural results. To enhance control, we present ObjCtrl-2.5D, a training-free object control approach that uses a 3D trajectory, extended from a 2D trajectory with depth information, as a control signal. By modeling object movement as camera movement, ObjCtrl-2.5D represents the 3D trajectory as a sequence of camera poses, enabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07721","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/2412.07721/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":"2412.07721","created_at":"2026-07-05T11:26:25.142063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07721v2","created_at":"2026-07-05T11:26:25.142063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07721","created_at":"2026-07-05T11:26:25.142063+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIXGDBWAHO7E","created_at":"2026-07-05T11:26:25.142063+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIXGDBWAHO7ENVQC","created_at":"2026-07-05T11:26:25.142063+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIXGDBWA","created_at":"2026-07-05T11:26:25.142063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01869","citing_title":"QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27575","citing_title":"Perceptual 3D Simulation With Physical World Modeling","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24321","citing_title":"Unified 3D Scene Understanding Through Physical World Modeling","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIXGDBWAHO7ENVQCV7EC3XEAVW","json":"https://pith.science/pith/GIXGDBWAHO7ENVQCV7EC3XEAVW.json","graph_json":"https://pith.science/api/pith-number/GIXGDBWAHO7ENVQCV7EC3XEAVW/graph.json","events_json":"https://pith.science/api/pith-number/GIXGDBWAHO7ENVQCV7EC3XEAVW/events.json","paper":"https://pith.science/paper/GIXGDBWA"},"agent_actions":{"view_html":"https://pith.science/pith/GIXGDBWAHO7ENVQCV7EC3XEAVW","download_json":"https://pith.science/pith/GIXGDBWAHO7ENVQCV7EC3XEAVW.json","view_paper":"https://pith.science/paper/GIXGDBWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07721&json=true","fetch_graph":"https://pith.science/api/pith-number/GIXGDBWAHO7ENVQCV7EC3XEAVW/graph.json","fetch_events":"https://pith.science/api/pith-number/GIXGDBWAHO7ENVQCV7EC3XEAVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIXGDBWAHO7ENVQCV7EC3XEAVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIXGDBWAHO7ENVQCV7EC3XEAVW/action/storage_attestation","attest_author":"https://pith.science/pith/GIXGDBWAHO7ENVQCV7EC3XEAVW/action/author_attestation","sign_citation":"https://pith.science/pith/GIXGDBWAHO7ENVQCV7EC3XEAVW/action/citation_signature","submit_replication":"https://pith.science/pith/GIXGDBWAHO7ENVQCV7EC3XEAVW/action/replication_record"}},"created_at":"2026-07-05T11:26:25.142063+00:00","updated_at":"2026-07-05T11:26:25.142063+00:00"}