{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KT5EC3OLRVW4HS4FGMXUDOV4AY","short_pith_number":"pith:KT5EC3OL","schema_version":"1.0","canonical_sha256":"54fa416dcb8d6dc3cb85332f41babc063140a527cf7c024370100b480310bb0b","source":{"kind":"arxiv","id":"2410.15957","version":3},"attestation_state":"computed","paper":{"title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangcong Zheng, Rui Jiang, Tao Wu, Teng Li, Xi Li, Yehao Lu","submitted_at":"2024-10-21T12:36:27Z","abstract_excerpt":"Recent advancements have integrated camera pose as a user-friendly and physics-informed condition in video diffusion models, enabling precise camera control. In this paper, we identify one of the key challenges as effectively modeling noisy cross-frame interactions to enhance geometry consistency and camera controllability. We innovatively associate the quality of a condition with its ability to reduce uncertainty and interpret noisy cross-frame features as a form of noisy condition. Recognizing that noisy conditions provide deterministic information while also introducing randomness and poten"},"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":"2410.15957","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T12:36:27Z","cross_cats_sorted":[],"title_canon_sha256":"7fe9080d745f358d55e7d052501518699b7311fb77ec298d218df22de8025f06","abstract_canon_sha256":"93430febaf79668584a864cc01ec1e1fcd685dce697d48969c8c20441e6d8952"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:15.815778Z","signature_b64":"pbMXOUrxQ13GmLeMhpkJuRmDOgI8btG3mlpH+6PhvRNXQJFDKS4OhPt8yh0eL8qkRXyfgGpt/mWrGYCFQuK5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54fa416dcb8d6dc3cb85332f41babc063140a527cf7c024370100b480310bb0b","last_reissued_at":"2026-07-05T09:44:15.815286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:15.815286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangcong Zheng, Rui Jiang, Tao Wu, Teng Li, Xi Li, Yehao Lu","submitted_at":"2024-10-21T12:36:27Z","abstract_excerpt":"Recent advancements have integrated camera pose as a user-friendly and physics-informed condition in video diffusion models, enabling precise camera control. In this paper, we identify one of the key challenges as effectively modeling noisy cross-frame interactions to enhance geometry consistency and camera controllability. We innovatively associate the quality of a condition with its ability to reduce uncertainty and interpret noisy cross-frame features as a form of noisy condition. Recognizing that noisy conditions provide deterministic information while also introducing randomness and poten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15957","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/2410.15957/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":"2410.15957","created_at":"2026-07-05T09:44:15.815352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15957v3","created_at":"2026-07-05T09:44:15.815352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15957","created_at":"2026-07-05T09:44:15.815352+00:00"},{"alias_kind":"pith_short_12","alias_value":"KT5EC3OLRVW4","created_at":"2026-07-05T09:44:15.815352+00:00"},{"alias_kind":"pith_short_16","alias_value":"KT5EC3OLRVW4HS4F","created_at":"2026-07-05T09:44:15.815352+00:00"},{"alias_kind":"pith_short_8","alias_value":"KT5EC3OL","created_at":"2026-07-05T09:44:15.815352+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2607.06216","citing_title":"MoWorld: A Flash World Model","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06291","citing_title":"AlayaWorld: Long-Horizon and Playable Video World Generation","ref_index":96,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24107","citing_title":"DramaDirector: Geometry-Guided Short Drama Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23105","citing_title":"Compression and Retrieval: Implicit Memory Retrieval for Video World Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20774","citing_title":"TriMotion: Modality-Agnostic Camera Control for Video Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13768","citing_title":"CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13432","citing_title":"OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07508","citing_title":"Streaming Video Generation with Streaming Force Control","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01590","citing_title":"Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26316","citing_title":"E$^3$C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27964","citing_title":"Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18365","citing_title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16937","citing_title":"DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28169","citing_title":"PhyCo: Learning Controllable Physical Priors for Generative Motion","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05187","citing_title":"LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08500","citing_title":"Novel View Synthesis as Video Completion","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KT5EC3OLRVW4HS4FGMXUDOV4AY","json":"https://pith.science/pith/KT5EC3OLRVW4HS4FGMXUDOV4AY.json","graph_json":"https://pith.science/api/pith-number/KT5EC3OLRVW4HS4FGMXUDOV4AY/graph.json","events_json":"https://pith.science/api/pith-number/KT5EC3OLRVW4HS4FGMXUDOV4AY/events.json","paper":"https://pith.science/paper/KT5EC3OL"},"agent_actions":{"view_html":"https://pith.science/pith/KT5EC3OLRVW4HS4FGMXUDOV4AY","download_json":"https://pith.science/pith/KT5EC3OLRVW4HS4FGMXUDOV4AY.json","view_paper":"https://pith.science/paper/KT5EC3OL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15957&json=true","fetch_graph":"https://pith.science/api/pith-number/KT5EC3OLRVW4HS4FGMXUDOV4AY/graph.json","fetch_events":"https://pith.science/api/pith-number/KT5EC3OLRVW4HS4FGMXUDOV4AY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KT5EC3OLRVW4HS4FGMXUDOV4AY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KT5EC3OLRVW4HS4FGMXUDOV4AY/action/storage_attestation","attest_author":"https://pith.science/pith/KT5EC3OLRVW4HS4FGMXUDOV4AY/action/author_attestation","sign_citation":"https://pith.science/pith/KT5EC3OLRVW4HS4FGMXUDOV4AY/action/citation_signature","submit_replication":"https://pith.science/pith/KT5EC3OLRVW4HS4FGMXUDOV4AY/action/replication_record"}},"created_at":"2026-07-05T09:44:15.815352+00:00","updated_at":"2026-07-05T09:44:15.815352+00:00"}