{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WMZR3532OCSADFKVFJLWMJD7CK","short_pith_number":"pith:WMZR3532","schema_version":"1.0","canonical_sha256":"b3331df77a70a40195552a5766247f129c96ca97c0ec918645eeb0ece1766836","source":{"kind":"arxiv","id":"2411.18613","version":2},"attestation_state":"computed","paper":{"title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Alex Trevithick, Ben Poole, Changxi Zheng, Jonathan T. Barron, Ruiqi Gao, Rundi Wu","submitted_at":"2024-11-27T18:57:16Z","abstract_excerpt":"We present CAT4D, a method for creating 4D (dynamic 3D) scenes from monocular video. CAT4D leverages a multi-view video diffusion model trained on a diverse combination of datasets to enable novel view synthesis at any specified camera poses and timestamps. Combined with a novel sampling approach, this model can transform a single monocular video into a multi-view video, enabling robust 4D reconstruction via optimization of a deformable 3D Gaussian representation. We demonstrate competitive performance on novel view synthesis and dynamic scene reconstruction benchmarks, and highlight the creat"},"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":"2411.18613","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T18:57:16Z","cross_cats_sorted":[],"title_canon_sha256":"57a125af8095a1ca774574e6bb6b9ba15d986a2387a813fe2db60d44801830c2","abstract_canon_sha256":"2229a0a57c1f8b8c873207a7a0a7e602eeb661bbc06fe2a9004b7fda4034e448"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:38.810736Z","signature_b64":"YxlNuwrlBnjxFP+Zi3Q4x5AmhuZNe9OnGYrYse9h+wpgIFUx+du8F5jSpxXEh9TKRRCdAi4MnURrPAGKbJDRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3331df77a70a40195552a5766247f129c96ca97c0ec918645eeb0ece1766836","last_reissued_at":"2026-07-05T09:51:38.809905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:38.809905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Alex Trevithick, Ben Poole, Changxi Zheng, Jonathan T. Barron, Ruiqi Gao, Rundi Wu","submitted_at":"2024-11-27T18:57:16Z","abstract_excerpt":"We present CAT4D, a method for creating 4D (dynamic 3D) scenes from monocular video. CAT4D leverages a multi-view video diffusion model trained on a diverse combination of datasets to enable novel view synthesis at any specified camera poses and timestamps. Combined with a novel sampling approach, this model can transform a single monocular video into a multi-view video, enabling robust 4D reconstruction via optimization of a deformable 3D Gaussian representation. We demonstrate competitive performance on novel view synthesis and dynamic scene reconstruction benchmarks, and highlight the creat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18613","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/2411.18613/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":"2411.18613","created_at":"2026-07-05T09:51:38.809974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18613v2","created_at":"2026-07-05T09:51:38.809974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18613","created_at":"2026-07-05T09:51:38.809974+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMZR3532OCSA","created_at":"2026-07-05T09:51:38.809974+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMZR3532OCSADFKV","created_at":"2026-07-05T09:51:38.809974+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMZR3532","created_at":"2026-07-05T09:51:38.809974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01590","citing_title":"Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31258","citing_title":"WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04876","citing_title":"PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18601","citing_title":"BulletGen: Improving 4D Reconstruction with Bullet-Time Generation","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00978","citing_title":"A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04527","citing_title":"Velox: Learning Representations of 4D Geometry and Appearance","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06168","citing_title":"Action Images: End-to-End Policy Learning via Multiview Video Generation","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMZR3532OCSADFKVFJLWMJD7CK","json":"https://pith.science/pith/WMZR3532OCSADFKVFJLWMJD7CK.json","graph_json":"https://pith.science/api/pith-number/WMZR3532OCSADFKVFJLWMJD7CK/graph.json","events_json":"https://pith.science/api/pith-number/WMZR3532OCSADFKVFJLWMJD7CK/events.json","paper":"https://pith.science/paper/WMZR3532"},"agent_actions":{"view_html":"https://pith.science/pith/WMZR3532OCSADFKVFJLWMJD7CK","download_json":"https://pith.science/pith/WMZR3532OCSADFKVFJLWMJD7CK.json","view_paper":"https://pith.science/paper/WMZR3532","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18613&json=true","fetch_graph":"https://pith.science/api/pith-number/WMZR3532OCSADFKVFJLWMJD7CK/graph.json","fetch_events":"https://pith.science/api/pith-number/WMZR3532OCSADFKVFJLWMJD7CK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMZR3532OCSADFKVFJLWMJD7CK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMZR3532OCSADFKVFJLWMJD7CK/action/storage_attestation","attest_author":"https://pith.science/pith/WMZR3532OCSADFKVFJLWMJD7CK/action/author_attestation","sign_citation":"https://pith.science/pith/WMZR3532OCSADFKVFJLWMJD7CK/action/citation_signature","submit_replication":"https://pith.science/pith/WMZR3532OCSADFKVFJLWMJD7CK/action/replication_record"}},"created_at":"2026-07-05T09:51:38.809974+00:00","updated_at":"2026-07-05T09:51:38.809974+00:00"}