{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K4LGUHLMYP5SO5LKDACD4AHNUF","short_pith_number":"pith:K4LGUHLM","schema_version":"1.0","canonical_sha256":"57166a1d6cc3fb27756a18043e00eda16ef512bbb15b483f5e16e455b466dab6","source":{"kind":"arxiv","id":"2412.07760","version":1},"attestation_state":"computed","paper":{"title":"SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Zhang, Haoji Hu, Jianhong Bai, Menghan Xia, Pengfei Wan, Xiao Fu, Xintao Wang, Ziyang Yuan, Zuozhu Liu","submitted_at":"2024-12-10T18:55:17Z","abstract_excerpt":"Recent advancements in video diffusion models have shown exceptional abilities in simulating real-world dynamics and maintaining 3D consistency. This progress inspires us to investigate the potential of these models to ensure dynamic consistency across various viewpoints, a highly desirable feature for applications such as virtual filming. Unlike existing methods focused on multi-view generation of single objects for 4D reconstruction, our interest lies in generating open-world videos from arbitrary viewpoints, incorporating 6 DoF camera poses. To achieve this, we propose a plug-and-play modul"},"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":"2412.07760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:55:17Z","cross_cats_sorted":[],"title_canon_sha256":"e4606fa7c4f32a69dee8dcc8be63ffaee4c0c7b616898b0c0db406ebda745b43","abstract_canon_sha256":"4464f005492a21de668304bee272b018a6b942ee2fb77b0cd1cf5a9ffde5ab52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:14.984526Z","signature_b64":"22qtB0fqjs1756sWINeJBVfLMaa0PmBjTLAB7V9nsb7TE8s2s60SsvW8AEnhKO2aNEsVIukbCr8eZKqlAhihAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57166a1d6cc3fb27756a18043e00eda16ef512bbb15b483f5e16e455b466dab6","last_reissued_at":"2026-07-05T09:47:14.983941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:14.983941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Zhang, Haoji Hu, Jianhong Bai, Menghan Xia, Pengfei Wan, Xiao Fu, Xintao Wang, Ziyang Yuan, Zuozhu Liu","submitted_at":"2024-12-10T18:55:17Z","abstract_excerpt":"Recent advancements in video diffusion models have shown exceptional abilities in simulating real-world dynamics and maintaining 3D consistency. This progress inspires us to investigate the potential of these models to ensure dynamic consistency across various viewpoints, a highly desirable feature for applications such as virtual filming. Unlike existing methods focused on multi-view generation of single objects for 4D reconstruction, our interest lies in generating open-world videos from arbitrary viewpoints, incorporating 6 DoF camera poses. To achieve this, we propose a plug-and-play modul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07760","kind":"arxiv","version":1},"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/2412.07760/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":"2412.07760","created_at":"2026-07-05T09:47:14.984004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07760v1","created_at":"2026-07-05T09:47:14.984004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07760","created_at":"2026-07-05T09:47:14.984004+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4LGUHLMYP5S","created_at":"2026-07-05T09:47:14.984004+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4LGUHLMYP5SO5LK","created_at":"2026-07-05T09:47:14.984004+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4LGUHLM","created_at":"2026-07-05T09:47:14.984004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05376","citing_title":"MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17536","citing_title":"OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14815","citing_title":"Probing into Camera Control of Video Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00299","citing_title":"Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11871","citing_title":"$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18365","citing_title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03181","citing_title":"SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11871","citing_title":"$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05207","citing_title":"Syn4D: A Multiview Synthetic 4D Dataset","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07990","citing_title":"SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations","ref_index":4,"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":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21776","citing_title":"Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4LGUHLMYP5SO5LKDACD4AHNUF","json":"https://pith.science/pith/K4LGUHLMYP5SO5LKDACD4AHNUF.json","graph_json":"https://pith.science/api/pith-number/K4LGUHLMYP5SO5LKDACD4AHNUF/graph.json","events_json":"https://pith.science/api/pith-number/K4LGUHLMYP5SO5LKDACD4AHNUF/events.json","paper":"https://pith.science/paper/K4LGUHLM"},"agent_actions":{"view_html":"https://pith.science/pith/K4LGUHLMYP5SO5LKDACD4AHNUF","download_json":"https://pith.science/pith/K4LGUHLMYP5SO5LKDACD4AHNUF.json","view_paper":"https://pith.science/paper/K4LGUHLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07760&json=true","fetch_graph":"https://pith.science/api/pith-number/K4LGUHLMYP5SO5LKDACD4AHNUF/graph.json","fetch_events":"https://pith.science/api/pith-number/K4LGUHLMYP5SO5LKDACD4AHNUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4LGUHLMYP5SO5LKDACD4AHNUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4LGUHLMYP5SO5LKDACD4AHNUF/action/storage_attestation","attest_author":"https://pith.science/pith/K4LGUHLMYP5SO5LKDACD4AHNUF/action/author_attestation","sign_citation":"https://pith.science/pith/K4LGUHLMYP5SO5LKDACD4AHNUF/action/citation_signature","submit_replication":"https://pith.science/pith/K4LGUHLMYP5SO5LKDACD4AHNUF/action/replication_record"}},"created_at":"2026-07-05T09:47:14.984004+00:00","updated_at":"2026-07-05T09:47:14.984004+00:00"}