{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JUPFFCPFICIWVLA3YDEYRGUQGA","short_pith_number":"pith:JUPFFCPF","schema_version":"1.0","canonical_sha256":"4d1e5289e540916aac1bc0c9889a9030128e0f9d0e0b0031df1143dfbc388a94","source":{"kind":"arxiv","id":"2411.18673","version":4},"attestation_state":"computed","paper":{"title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Andrea Tagliasacchi, David B. Lindell, Guocheng Qian, Ivan Skorokhodov, Sergey Tulyakov, Sherwin Bahmani, Willi Menapace","submitted_at":"2024-11-27T18:49:13Z","abstract_excerpt":"Numerous works have recently integrated 3D camera control into foundational text-to-video models, but the resulting camera control is often imprecise, and video generation quality suffers. In this work, we analyze camera motion from a first principles perspective, uncovering insights that enable precise 3D camera manipulation without compromising synthesis quality. First, we determine that motion induced by camera movements in videos is low-frequency in nature. This motivates us to adjust train and test pose conditioning schedules, accelerating training convergence while improving visual and m"},"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":"2411.18673","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T18:49:13Z","cross_cats_sorted":[],"title_canon_sha256":"e162d4812fba7d7ef6c882c85f89a5f1e28d3d4654cb2faa42b7a64b3e22a148","abstract_canon_sha256":"afbff96c2e773839cdc3db178dee93f86f24c25a3ed0a7d7dd4aa4b883b798b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:03.968801Z","signature_b64":"hMmis0GuYn1PTtey5FfUTCgHZxcmJudJjv4dBh9NkyHi8dPop+gWD+9iNs3gEpvpOGDOZiwqfpDlheZGHKgMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d1e5289e540916aac1bc0c9889a9030128e0f9d0e0b0031df1143dfbc388a94","last_reissued_at":"2026-07-05T10:59:03.968272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:03.968272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Andrea Tagliasacchi, David B. Lindell, Guocheng Qian, Ivan Skorokhodov, Sergey Tulyakov, Sherwin Bahmani, Willi Menapace","submitted_at":"2024-11-27T18:49:13Z","abstract_excerpt":"Numerous works have recently integrated 3D camera control into foundational text-to-video models, but the resulting camera control is often imprecise, and video generation quality suffers. In this work, we analyze camera motion from a first principles perspective, uncovering insights that enable precise 3D camera manipulation without compromising synthesis quality. First, we determine that motion induced by camera movements in videos is low-frequency in nature. This motivates us to adjust train and test pose conditioning schedules, accelerating training convergence while improving visual and m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18673","kind":"arxiv","version":4},"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/2411.18673/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":"2411.18673","created_at":"2026-07-05T10:59:03.968340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18673v4","created_at":"2026-07-05T10:59:03.968340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18673","created_at":"2026-07-05T10:59:03.968340+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUPFFCPFICIW","created_at":"2026-07-05T10:59:03.968340+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUPFFCPFICIWVLA3","created_at":"2026-07-05T10:59:03.968340+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUPFFCPF","created_at":"2026-07-05T10:59:03.968340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30855","citing_title":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22481","citing_title":"Lighting-Consistent Object Transfer Across Radiance Fields","ref_index":224,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":233,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04911","citing_title":"SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUPFFCPFICIWVLA3YDEYRGUQGA","json":"https://pith.science/pith/JUPFFCPFICIWVLA3YDEYRGUQGA.json","graph_json":"https://pith.science/api/pith-number/JUPFFCPFICIWVLA3YDEYRGUQGA/graph.json","events_json":"https://pith.science/api/pith-number/JUPFFCPFICIWVLA3YDEYRGUQGA/events.json","paper":"https://pith.science/paper/JUPFFCPF"},"agent_actions":{"view_html":"https://pith.science/pith/JUPFFCPFICIWVLA3YDEYRGUQGA","download_json":"https://pith.science/pith/JUPFFCPFICIWVLA3YDEYRGUQGA.json","view_paper":"https://pith.science/paper/JUPFFCPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18673&json=true","fetch_graph":"https://pith.science/api/pith-number/JUPFFCPFICIWVLA3YDEYRGUQGA/graph.json","fetch_events":"https://pith.science/api/pith-number/JUPFFCPFICIWVLA3YDEYRGUQGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUPFFCPFICIWVLA3YDEYRGUQGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUPFFCPFICIWVLA3YDEYRGUQGA/action/storage_attestation","attest_author":"https://pith.science/pith/JUPFFCPFICIWVLA3YDEYRGUQGA/action/author_attestation","sign_citation":"https://pith.science/pith/JUPFFCPFICIWVLA3YDEYRGUQGA/action/citation_signature","submit_replication":"https://pith.science/pith/JUPFFCPFICIWVLA3YDEYRGUQGA/action/replication_record"}},"created_at":"2026-07-05T10:59:03.968340+00:00","updated_at":"2026-07-05T10:59:03.968340+00:00"}