{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SMC2AYB6Y3ZEVZ65BK3V7VURDT","short_pith_number":"pith:SMC2AYB6","schema_version":"1.0","canonical_sha256":"9305a0603ec6f24ae7dd0ab75fd6911cee3679a84a1ff9fb25a38574de8eeef6","source":{"kind":"arxiv","id":"2410.24203","version":1},"attestation_state":"computed","paper":{"title":"DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.RO"],"primary_cat":"cs.CV","authors_text":"Cairong Zhao, Chenhao Ji, Guofeng Zhang, Junyao Gao, Song-Hai Zhang, Tong He, Wanli Ouyang, Weicai Ye, Xiaoshui Huang, Zheng Chen","submitted_at":"2024-10-31T17:57:02Z","abstract_excerpt":"Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of generating consistent multi-view images. To address these issues, we first establish a large-scale panoramic video-text dataset containing millions of consecutive panoramic keyframes with corresponding panoramic depths, camera poses, and text descriptions. Then, we propose a novel text-driven panoramic ge"},"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":"2410.24203","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T17:57:02Z","cross_cats_sorted":["cs.AI","cs.GR","cs.RO"],"title_canon_sha256":"ed31402526a845f56a9be86f62f887cdeaf5d4832506b2ef1d40054ae2dca858","abstract_canon_sha256":"89098cc06580ec099d76dc8550e6877867ca5c90f238588cd65fcc5eb1a9bf88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:21.185991Z","signature_b64":"e2OkXlKlTLg2Y/fbkUWQbyDByqOSMxlJNXBesBYNKOp+2a0e8XbUMra8jmzZoDA5ActteCcRcfjqoI4EujlbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9305a0603ec6f24ae7dd0ab75fd6911cee3679a84a1ff9fb25a38574de8eeef6","last_reissued_at":"2026-07-05T09:29:21.185451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:21.185451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.RO"],"primary_cat":"cs.CV","authors_text":"Cairong Zhao, Chenhao Ji, Guofeng Zhang, Junyao Gao, Song-Hai Zhang, Tong He, Wanli Ouyang, Weicai Ye, Xiaoshui Huang, Zheng Chen","submitted_at":"2024-10-31T17:57:02Z","abstract_excerpt":"Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of generating consistent multi-view images. To address these issues, we first establish a large-scale panoramic video-text dataset containing millions of consecutive panoramic keyframes with corresponding panoramic depths, camera poses, and text descriptions. Then, we propose a novel text-driven panoramic ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24203","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/2410.24203/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":"2410.24203","created_at":"2026-07-05T09:29:21.185549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.24203v1","created_at":"2026-07-05T09:29:21.185549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24203","created_at":"2026-07-05T09:29:21.185549+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMC2AYB6Y3ZE","created_at":"2026-07-05T09:29:21.185549+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMC2AYB6Y3ZEVZ65","created_at":"2026-07-05T09:29:21.185549+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMC2AYB6","created_at":"2026-07-05T09:29:21.185549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24642","citing_title":"Probing CLIP's Comprehension of 360-Degree Textual and Visual Semantics","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMC2AYB6Y3ZEVZ65BK3V7VURDT","json":"https://pith.science/pith/SMC2AYB6Y3ZEVZ65BK3V7VURDT.json","graph_json":"https://pith.science/api/pith-number/SMC2AYB6Y3ZEVZ65BK3V7VURDT/graph.json","events_json":"https://pith.science/api/pith-number/SMC2AYB6Y3ZEVZ65BK3V7VURDT/events.json","paper":"https://pith.science/paper/SMC2AYB6"},"agent_actions":{"view_html":"https://pith.science/pith/SMC2AYB6Y3ZEVZ65BK3V7VURDT","download_json":"https://pith.science/pith/SMC2AYB6Y3ZEVZ65BK3V7VURDT.json","view_paper":"https://pith.science/paper/SMC2AYB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.24203&json=true","fetch_graph":"https://pith.science/api/pith-number/SMC2AYB6Y3ZEVZ65BK3V7VURDT/graph.json","fetch_events":"https://pith.science/api/pith-number/SMC2AYB6Y3ZEVZ65BK3V7VURDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMC2AYB6Y3ZEVZ65BK3V7VURDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMC2AYB6Y3ZEVZ65BK3V7VURDT/action/storage_attestation","attest_author":"https://pith.science/pith/SMC2AYB6Y3ZEVZ65BK3V7VURDT/action/author_attestation","sign_citation":"https://pith.science/pith/SMC2AYB6Y3ZEVZ65BK3V7VURDT/action/citation_signature","submit_replication":"https://pith.science/pith/SMC2AYB6Y3ZEVZ65BK3V7VURDT/action/replication_record"}},"created_at":"2026-07-05T09:29:21.185549+00:00","updated_at":"2026-07-05T09:29:21.185549+00:00"}