{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6BGMQQI52T3S57YBQZ2RAKOKDB","short_pith_number":"pith:6BGMQQI5","schema_version":"1.0","canonical_sha256":"f04cc8411dd4f72eff0186751029ca18744ff415c3640b58697f7f9506e2e64a","source":{"kind":"arxiv","id":"2504.11389","version":2},"attestation_state":"computed","paper":{"title":"VideoPanda: Video Panoramic Diffusion with Multi-view Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Amirmojtaba Sabour, Despoina Paschalidou, Greg Klar, Jiahui Huang, Kevin Xie, Sanja Fidler, Umar Iqbal, Xiaohui Zeng","submitted_at":"2025-04-15T16:58:15Z","abstract_excerpt":"High resolution panoramic video content is paramount for immersive experiences in Virtual Reality, but is non-trivial to collect as it requires specialized equipment and intricate camera setups. In this work, we introduce VideoPanda, a novel approach for synthesizing 360$^\\circ$ videos conditioned on text or single-view video data. VideoPanda leverages multi-view attention layers to augment a video diffusion model, enabling it to generate consistent multi-view videos that can be combined into immersive panoramic content. VideoPanda is trained jointly using two conditions: text-only and single-"},"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":"2504.11389","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2025-04-15T16:58:15Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e57f7db413e0bfdafe5fffb3457fb660a37d63f79b00ea4d79e2ae7171a7bd22","abstract_canon_sha256":"3b630f5ad1b14306116e5bb6495aeec8ca5f37ab32eebb003742106cbab44272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:49.083267Z","signature_b64":"klbG8KgvxmvhM0CW6ArlqY39xRkVvbhzCwa4HZpDrNI6/0zfhfrEAvrFTL+UyJXacIptzFrKlUdgAQHNehhtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f04cc8411dd4f72eff0186751029ca18744ff415c3640b58697f7f9506e2e64a","last_reissued_at":"2026-07-05T10:50:49.082746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:49.082746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoPanda: Video Panoramic Diffusion with Multi-view Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Amirmojtaba Sabour, Despoina Paschalidou, Greg Klar, Jiahui Huang, Kevin Xie, Sanja Fidler, Umar Iqbal, Xiaohui Zeng","submitted_at":"2025-04-15T16:58:15Z","abstract_excerpt":"High resolution panoramic video content is paramount for immersive experiences in Virtual Reality, but is non-trivial to collect as it requires specialized equipment and intricate camera setups. In this work, we introduce VideoPanda, a novel approach for synthesizing 360$^\\circ$ videos conditioned on text or single-view video data. VideoPanda leverages multi-view attention layers to augment a video diffusion model, enabling it to generate consistent multi-view videos that can be combined into immersive panoramic content. VideoPanda is trained jointly using two conditions: text-only and single-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11389","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/2504.11389/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":"2504.11389","created_at":"2026-07-05T10:50:49.082809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11389v2","created_at":"2026-07-05T10:50:49.082809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11389","created_at":"2026-07-05T10:50:49.082809+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BGMQQI52T3S","created_at":"2026-07-05T10:50:49.082809+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BGMQQI52T3S57YB","created_at":"2026-07-05T10:50:49.082809+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BGMQQI5","created_at":"2026-07-05T10:50:49.082809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05162","citing_title":"Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10578","citing_title":"Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BGMQQI52T3S57YBQZ2RAKOKDB","json":"https://pith.science/pith/6BGMQQI52T3S57YBQZ2RAKOKDB.json","graph_json":"https://pith.science/api/pith-number/6BGMQQI52T3S57YBQZ2RAKOKDB/graph.json","events_json":"https://pith.science/api/pith-number/6BGMQQI52T3S57YBQZ2RAKOKDB/events.json","paper":"https://pith.science/paper/6BGMQQI5"},"agent_actions":{"view_html":"https://pith.science/pith/6BGMQQI52T3S57YBQZ2RAKOKDB","download_json":"https://pith.science/pith/6BGMQQI52T3S57YBQZ2RAKOKDB.json","view_paper":"https://pith.science/paper/6BGMQQI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11389&json=true","fetch_graph":"https://pith.science/api/pith-number/6BGMQQI52T3S57YBQZ2RAKOKDB/graph.json","fetch_events":"https://pith.science/api/pith-number/6BGMQQI52T3S57YBQZ2RAKOKDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BGMQQI52T3S57YBQZ2RAKOKDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BGMQQI52T3S57YBQZ2RAKOKDB/action/storage_attestation","attest_author":"https://pith.science/pith/6BGMQQI52T3S57YBQZ2RAKOKDB/action/author_attestation","sign_citation":"https://pith.science/pith/6BGMQQI52T3S57YBQZ2RAKOKDB/action/citation_signature","submit_replication":"https://pith.science/pith/6BGMQQI52T3S57YBQZ2RAKOKDB/action/replication_record"}},"created_at":"2026-07-05T10:50:49.082809+00:00","updated_at":"2026-07-05T10:50:49.082809+00:00"}