{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FE7OCGPRP77GJIEX2PRQI5MSS4","short_pith_number":"pith:FE7OCGPR","schema_version":"1.0","canonical_sha256":"293ee119f17ffe64a097d3e304759297351aed389471c838ab25375d92598ad7","source":{"kind":"arxiv","id":"2503.09151","version":3},"attestation_state":"computed","paper":{"title":"Reangle-A-Video: 4D Video Generation as Video-to-Video Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hyeonho Jeong, Jong Chul Ye, Suhyeon Lee","submitted_at":"2025-03-12T08:26:15Z","abstract_excerpt":"We introduce Reangle-A-Video, a unified framework for generating synchronized multi-view videos from a single input video. Unlike mainstream approaches that train multi-view video diffusion models on large-scale 4D datasets, our method reframes the multi-view video generation task as video-to-videos translation, leveraging publicly available image and video diffusion priors. In essence, Reangle-A-Video operates in two stages. (1) Multi-View Motion Learning: An image-to-video diffusion transformer is synchronously fine-tuned in a self-supervised manner to distill view-invariant motion from a se"},"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":"2503.09151","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T08:26:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df9cf164776d7a32c292a8630bf972444d0f0c155a9ae023f43d0a185cd9990f","abstract_canon_sha256":"ce8d0514aa9a0de085a1a278659522e7fbc0bc19c327c3f215c63a6849902da1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:00.935090Z","signature_b64":"6Jtma1pOtTnU9ERgBBvCVNFcKWGS77UcSnf0gEXaDHbVmIdknl/k2ZtHA3YmWU2uYCI9+p9JYOfIs3g88wwHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"293ee119f17ffe64a097d3e304759297351aed389471c838ab25375d92598ad7","last_reissued_at":"2026-07-05T12:08:00.934635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:00.934635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reangle-A-Video: 4D Video Generation as Video-to-Video Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hyeonho Jeong, Jong Chul Ye, Suhyeon Lee","submitted_at":"2025-03-12T08:26:15Z","abstract_excerpt":"We introduce Reangle-A-Video, a unified framework for generating synchronized multi-view videos from a single input video. Unlike mainstream approaches that train multi-view video diffusion models on large-scale 4D datasets, our method reframes the multi-view video generation task as video-to-videos translation, leveraging publicly available image and video diffusion priors. In essence, Reangle-A-Video operates in two stages. (1) Multi-View Motion Learning: An image-to-video diffusion transformer is synchronously fine-tuned in a self-supervised manner to distill view-invariant motion from a se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09151","kind":"arxiv","version":3},"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/2503.09151/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":"2503.09151","created_at":"2026-07-05T12:08:00.934692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09151v3","created_at":"2026-07-05T12:08:00.934692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09151","created_at":"2026-07-05T12:08:00.934692+00:00"},{"alias_kind":"pith_short_12","alias_value":"FE7OCGPRP77G","created_at":"2026-07-05T12:08:00.934692+00:00"},{"alias_kind":"pith_short_16","alias_value":"FE7OCGPRP77GJIEX","created_at":"2026-07-05T12:08:00.934692+00:00"},{"alias_kind":"pith_short_8","alias_value":"FE7OCGPR","created_at":"2026-07-05T12:08:00.934692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17310","citing_title":"SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01799","citing_title":"Embody4D: A Generalist Data Engine for Embodied 4D World Modeling","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12119","citing_title":"MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12119","citing_title":"MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics","ref_index":16,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01799","citing_title":"Embody4D: A Generalist Data Engine for Embodied 4D World Modeling","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FE7OCGPRP77GJIEX2PRQI5MSS4","json":"https://pith.science/pith/FE7OCGPRP77GJIEX2PRQI5MSS4.json","graph_json":"https://pith.science/api/pith-number/FE7OCGPRP77GJIEX2PRQI5MSS4/graph.json","events_json":"https://pith.science/api/pith-number/FE7OCGPRP77GJIEX2PRQI5MSS4/events.json","paper":"https://pith.science/paper/FE7OCGPR"},"agent_actions":{"view_html":"https://pith.science/pith/FE7OCGPRP77GJIEX2PRQI5MSS4","download_json":"https://pith.science/pith/FE7OCGPRP77GJIEX2PRQI5MSS4.json","view_paper":"https://pith.science/paper/FE7OCGPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09151&json=true","fetch_graph":"https://pith.science/api/pith-number/FE7OCGPRP77GJIEX2PRQI5MSS4/graph.json","fetch_events":"https://pith.science/api/pith-number/FE7OCGPRP77GJIEX2PRQI5MSS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FE7OCGPRP77GJIEX2PRQI5MSS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FE7OCGPRP77GJIEX2PRQI5MSS4/action/storage_attestation","attest_author":"https://pith.science/pith/FE7OCGPRP77GJIEX2PRQI5MSS4/action/author_attestation","sign_citation":"https://pith.science/pith/FE7OCGPRP77GJIEX2PRQI5MSS4/action/citation_signature","submit_replication":"https://pith.science/pith/FE7OCGPRP77GJIEX2PRQI5MSS4/action/replication_record"}},"created_at":"2026-07-05T12:08:00.934692+00:00","updated_at":"2026-07-05T12:08:00.934692+00:00"}