{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VM6XCLXLMGSCTWXDN2JQLQLY7J","short_pith_number":"pith:VM6XCLXL","schema_version":"1.0","canonical_sha256":"ab3d712eeb61a429dae36e9305c178fa60aa57f86d213049fada129634d775e7","source":{"kind":"arxiv","id":"2406.10126","version":4},"attestation_state":"computed","paper":{"title":"Training-free Camera Control for Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Hou, Zhibo Chen","submitted_at":"2024-06-14T15:33:00Z","abstract_excerpt":"We propose a training-free and robust solution to offer camera movement control for off-the-shelf video diffusion models. Unlike previous work, our method does not require any supervised finetuning on camera-annotated datasets or self-supervised training via data augmentation. Instead, it can be plug-and-play with most pretrained video diffusion models and generate camera-controllable videos with a single image or text prompt as input. The inspiration for our work comes from the layout prior that intermediate latents encode for the generated results, thus rearranging noisy pixels in them will "},"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":"2406.10126","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T15:33:00Z","cross_cats_sorted":[],"title_canon_sha256":"942e64e7d80206bceacefb291054eda61ba022fe7e0dae98410c67d62ec392eb","abstract_canon_sha256":"8a2c3a367b34c3c09182692db12d82ccf96060f84f2d0e71bbff5f6ee2b217c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:25.278157Z","signature_b64":"v54/uDMDKtS3olfHhtIyMQ08NHu+7fqQD8tEdYflAJwYNbtv0eaML/n4YNqJLp9oSBgMu9UiHsEdNaNTqb+qBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab3d712eeb61a429dae36e9305c178fa60aa57f86d213049fada129634d775e7","last_reissued_at":"2026-07-05T10:19:25.277677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:25.277677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-free Camera Control for Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Hou, Zhibo Chen","submitted_at":"2024-06-14T15:33:00Z","abstract_excerpt":"We propose a training-free and robust solution to offer camera movement control for off-the-shelf video diffusion models. Unlike previous work, our method does not require any supervised finetuning on camera-annotated datasets or self-supervised training via data augmentation. Instead, it can be plug-and-play with most pretrained video diffusion models and generate camera-controllable videos with a single image or text prompt as input. The inspiration for our work comes from the layout prior that intermediate latents encode for the generated results, thus rearranging noisy pixels in them will "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10126","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/2406.10126/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":"2406.10126","created_at":"2026-07-05T10:19:25.277734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10126v4","created_at":"2026-07-05T10:19:25.277734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10126","created_at":"2026-07-05T10:19:25.277734+00:00"},{"alias_kind":"pith_short_12","alias_value":"VM6XCLXLMGSC","created_at":"2026-07-05T10:19:25.277734+00:00"},{"alias_kind":"pith_short_16","alias_value":"VM6XCLXLMGSCTWXD","created_at":"2026-07-05T10:19:25.277734+00:00"},{"alias_kind":"pith_short_8","alias_value":"VM6XCLXL","created_at":"2026-07-05T10:19:25.277734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06291","citing_title":"AlayaWorld: Long-Horizon and Playable Video World Generation","ref_index":24,"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":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26092","citing_title":"TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24829","citing_title":"GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01869","citing_title":"QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01590","citing_title":"Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14815","citing_title":"Probing into Camera Control of Video Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25266","citing_title":"DeltaCam: Differential Intrinsic Camera Modeling for Video Generation","ref_index":15,"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":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00499","citing_title":"OptiWorld: Optimal Control for Video World Generation under Physical Constraints","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11871","citing_title":"$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15182","citing_title":"Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11871","citing_title":"$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2404.02101","citing_title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","ref_index":87,"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":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06051","citing_title":"RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":229,"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":36,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13793","citing_title":"From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16733","citing_title":"Active World-Model with 4D-informed Retrieval for Exploration and Awareness","ref_index":3,"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":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VM6XCLXLMGSCTWXDN2JQLQLY7J","json":"https://pith.science/pith/VM6XCLXLMGSCTWXDN2JQLQLY7J.json","graph_json":"https://pith.science/api/pith-number/VM6XCLXLMGSCTWXDN2JQLQLY7J/graph.json","events_json":"https://pith.science/api/pith-number/VM6XCLXLMGSCTWXDN2JQLQLY7J/events.json","paper":"https://pith.science/paper/VM6XCLXL"},"agent_actions":{"view_html":"https://pith.science/pith/VM6XCLXLMGSCTWXDN2JQLQLY7J","download_json":"https://pith.science/pith/VM6XCLXLMGSCTWXDN2JQLQLY7J.json","view_paper":"https://pith.science/paper/VM6XCLXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10126&json=true","fetch_graph":"https://pith.science/api/pith-number/VM6XCLXLMGSCTWXDN2JQLQLY7J/graph.json","fetch_events":"https://pith.science/api/pith-number/VM6XCLXLMGSCTWXDN2JQLQLY7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VM6XCLXLMGSCTWXDN2JQLQLY7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VM6XCLXLMGSCTWXDN2JQLQLY7J/action/storage_attestation","attest_author":"https://pith.science/pith/VM6XCLXLMGSCTWXDN2JQLQLY7J/action/author_attestation","sign_citation":"https://pith.science/pith/VM6XCLXLMGSCTWXDN2JQLQLY7J/action/citation_signature","submit_replication":"https://pith.science/pith/VM6XCLXLMGSCTWXDN2JQLQLY7J/action/replication_record"}},"created_at":"2026-07-05T10:19:25.277734+00:00","updated_at":"2026-07-05T10:19:25.277734+00:00"}