{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TI44NMLXBWPKV3B76SNLMMW5OK","short_pith_number":"pith:TI44NMLX","schema_version":"1.0","canonical_sha256":"9a39c6b1770d9eaaec3ff49ab632dd72a6386b6c99505fedb05cd855fd2890ca","source":{"kind":"arxiv","id":"2504.14906","version":3},"attestation_state":"computed","paper":{"title":"OmniAudio: Generating Spatial Audio from 360-Degree Video","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Huadai Liu, Jialei Wang, Kaicheng Luo, Peiwen Sun, Qian Chen, Qikai Jiang, Rongjie Huang, Shiliang Zhang, Tianyi Luo, Wei Xue, Wen Wang, Xiangtai Li, Zhijie Yan, Zhou Zhao","submitted_at":"2025-04-21T07:21:28Z","abstract_excerpt":"Traditional video-to-audio generation techniques primarily focus on perspective video and non-spatial audio, often missing the spatial cues necessary for accurately representing sound sources in 3D environments. To address this limitation, we introduce a novel task, 360V2SA, to generate spatial audio from 360-degree videos, specifically producing First-order Ambisonics (FOA) audio - a standard format for representing 3D spatial audio that captures sound directionality and enables realistic 3D audio reproduction. We first create Sphere360, a novel dataset tailored for this task that is curated "},"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":"2504.14906","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2025-04-21T07:21:28Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"0db8bf5af10b75159d66e76d10c25501260fbb969cfc953217005f77f006b89c","abstract_canon_sha256":"ab6108a66833113036a4b53901205e2461d8ca9a415fe3345b9780bd04bdadc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:28.651394Z","signature_b64":"5NUUgNs0AN7P2x+cexSWLrOQrcjV+Fj4r09BlezeuIjBPymPJT1jFp7RlOp2UX3HCEFezqN4C1Nkjwf2vG75CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a39c6b1770d9eaaec3ff49ab632dd72a6386b6c99505fedb05cd855fd2890ca","last_reissued_at":"2026-07-05T11:14:28.650909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:28.650909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniAudio: Generating Spatial Audio from 360-Degree Video","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Huadai Liu, Jialei Wang, Kaicheng Luo, Peiwen Sun, Qian Chen, Qikai Jiang, Rongjie Huang, Shiliang Zhang, Tianyi Luo, Wei Xue, Wen Wang, Xiangtai Li, Zhijie Yan, Zhou Zhao","submitted_at":"2025-04-21T07:21:28Z","abstract_excerpt":"Traditional video-to-audio generation techniques primarily focus on perspective video and non-spatial audio, often missing the spatial cues necessary for accurately representing sound sources in 3D environments. To address this limitation, we introduce a novel task, 360V2SA, to generate spatial audio from 360-degree videos, specifically producing First-order Ambisonics (FOA) audio - a standard format for representing 3D spatial audio that captures sound directionality and enables realistic 3D audio reproduction. We first create Sphere360, a novel dataset tailored for this task that is curated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14906","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/2504.14906/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":"2504.14906","created_at":"2026-07-05T11:14:28.650968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14906v3","created_at":"2026-07-05T11:14:28.650968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14906","created_at":"2026-07-05T11:14:28.650968+00:00"},{"alias_kind":"pith_short_12","alias_value":"TI44NMLXBWPK","created_at":"2026-07-05T11:14:28.650968+00:00"},{"alias_kind":"pith_short_16","alias_value":"TI44NMLXBWPKV3B7","created_at":"2026-07-05T11:14:28.650968+00:00"},{"alias_kind":"pith_short_8","alias_value":"TI44NMLX","created_at":"2026-07-05T11:14:28.650968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30940","citing_title":"Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18272","citing_title":"StereoFoley: Object-Aware Stereo Audio Generation from Video","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05731","citing_title":"FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TI44NMLXBWPKV3B76SNLMMW5OK","json":"https://pith.science/pith/TI44NMLXBWPKV3B76SNLMMW5OK.json","graph_json":"https://pith.science/api/pith-number/TI44NMLXBWPKV3B76SNLMMW5OK/graph.json","events_json":"https://pith.science/api/pith-number/TI44NMLXBWPKV3B76SNLMMW5OK/events.json","paper":"https://pith.science/paper/TI44NMLX"},"agent_actions":{"view_html":"https://pith.science/pith/TI44NMLXBWPKV3B76SNLMMW5OK","download_json":"https://pith.science/pith/TI44NMLXBWPKV3B76SNLMMW5OK.json","view_paper":"https://pith.science/paper/TI44NMLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14906&json=true","fetch_graph":"https://pith.science/api/pith-number/TI44NMLXBWPKV3B76SNLMMW5OK/graph.json","fetch_events":"https://pith.science/api/pith-number/TI44NMLXBWPKV3B76SNLMMW5OK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TI44NMLXBWPKV3B76SNLMMW5OK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TI44NMLXBWPKV3B76SNLMMW5OK/action/storage_attestation","attest_author":"https://pith.science/pith/TI44NMLXBWPKV3B76SNLMMW5OK/action/author_attestation","sign_citation":"https://pith.science/pith/TI44NMLXBWPKV3B76SNLMMW5OK/action/citation_signature","submit_replication":"https://pith.science/pith/TI44NMLXBWPKV3B76SNLMMW5OK/action/replication_record"}},"created_at":"2026-07-05T11:14:28.650968+00:00","updated_at":"2026-07-05T11:14:28.650968+00:00"}