{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JOPY3MVRVIY6YMW6PQDZYEEQEG","short_pith_number":"pith:JOPY3MVR","schema_version":"1.0","canonical_sha256":"4b9f8db2b1aa31ec32de7c079c10902197abb201c3d2ea993cff8a420deaf0b6","source":{"kind":"arxiv","id":"2502.10059","version":2},"attestation_state":"computed","paper":{"title":"RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanyun Deng, Guangcong Zheng, Lin Cheng, Min Chen, Rui Jiang, Shuigen Zhan, Tao Wu, Teng Li, Xi Li, Yehao Lu, Yepan Xiong, Yining Lin","submitted_at":"2025-02-14T10:21:49Z","abstract_excerpt":"Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant usability challenges, as users often struggle to provide precise camera parameters when working with arbitrary real-world images without knowledge of their depth nor scene scale. To address these real-world application issues, we propose RealCam-I2V, a novel diffusion-based video generation framework that integrates monocular metric depth estimation to establish 3D scene reconst"},"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":"2502.10059","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T10:21:49Z","cross_cats_sorted":[],"title_canon_sha256":"8502dcf7cea5e599c372591f7c11c7f6fbdb5f65fc3d42c4708a4b9b70fb4591","abstract_canon_sha256":"d760709f3ed55e404e644d642a93c76d693124a83014fe83a5105b93c24974bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:53.553618Z","signature_b64":"+YTfSAvTDUAFTHf7JIHMgOQgRAYfW0XerUKjs+7WfG6s+/yRzCZ6GCxWm8cJGk+Wt1MiCDLXmeEbPzetDTVaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b9f8db2b1aa31ec32de7c079c10902197abb201c3d2ea993cff8a420deaf0b6","last_reissued_at":"2026-07-05T11:35:53.553097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:53.553097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanyun Deng, Guangcong Zheng, Lin Cheng, Min Chen, Rui Jiang, Shuigen Zhan, Tao Wu, Teng Li, Xi Li, Yehao Lu, Yepan Xiong, Yining Lin","submitted_at":"2025-02-14T10:21:49Z","abstract_excerpt":"Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant usability challenges, as users often struggle to provide precise camera parameters when working with arbitrary real-world images without knowledge of their depth nor scene scale. To address these real-world application issues, we propose RealCam-I2V, a novel diffusion-based video generation framework that integrates monocular metric depth estimation to establish 3D scene reconst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10059","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/2502.10059/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":"2502.10059","created_at":"2026-07-05T11:35:53.553161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10059v2","created_at":"2026-07-05T11:35:53.553161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10059","created_at":"2026-07-05T11:35:53.553161+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOPY3MVRVIY6","created_at":"2026-07-05T11:35:53.553161+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOPY3MVRVIY6YMW6","created_at":"2026-07-05T11:35:53.553161+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOPY3MVR","created_at":"2026-07-05T11:35:53.553161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20774","citing_title":"TriMotion: Modality-Agnostic Camera Control for Video Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01590","citing_title":"Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30855","citing_title":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07209","citing_title":"INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06010","citing_title":"OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOPY3MVRVIY6YMW6PQDZYEEQEG","json":"https://pith.science/pith/JOPY3MVRVIY6YMW6PQDZYEEQEG.json","graph_json":"https://pith.science/api/pith-number/JOPY3MVRVIY6YMW6PQDZYEEQEG/graph.json","events_json":"https://pith.science/api/pith-number/JOPY3MVRVIY6YMW6PQDZYEEQEG/events.json","paper":"https://pith.science/paper/JOPY3MVR"},"agent_actions":{"view_html":"https://pith.science/pith/JOPY3MVRVIY6YMW6PQDZYEEQEG","download_json":"https://pith.science/pith/JOPY3MVRVIY6YMW6PQDZYEEQEG.json","view_paper":"https://pith.science/paper/JOPY3MVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10059&json=true","fetch_graph":"https://pith.science/api/pith-number/JOPY3MVRVIY6YMW6PQDZYEEQEG/graph.json","fetch_events":"https://pith.science/api/pith-number/JOPY3MVRVIY6YMW6PQDZYEEQEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOPY3MVRVIY6YMW6PQDZYEEQEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOPY3MVRVIY6YMW6PQDZYEEQEG/action/storage_attestation","attest_author":"https://pith.science/pith/JOPY3MVRVIY6YMW6PQDZYEEQEG/action/author_attestation","sign_citation":"https://pith.science/pith/JOPY3MVRVIY6YMW6PQDZYEEQEG/action/citation_signature","submit_replication":"https://pith.science/pith/JOPY3MVRVIY6YMW6PQDZYEEQEG/action/replication_record"}},"created_at":"2026-07-05T11:35:53.553161+00:00","updated_at":"2026-07-05T11:35:53.553161+00:00"}