{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OAH2VGWCSWRISABCCSDLRGZXRV","short_pith_number":"pith:OAH2VGWC","schema_version":"1.0","canonical_sha256":"700faa9ac295a28900221486b89b378d7e800ad039e33b885b8a7b9bc6e9c6f7","source":{"kind":"arxiv","id":"2302.02088","version":3},"attestation_state":"computed","paper":{"title":"AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Anurag Kumar, Chao Huang, Chenliang Xu, Susan Liang, Yapeng Tian","submitted_at":"2023-02-04T04:17:19Z","abstract_excerpt":"Can machines recording an audio-visual scene produce realistic, matching audio-visual experiences at novel positions and novel view directions? We answer it by studying a new task -- real-world audio-visual scene synthesis -- and a first-of-its-kind NeRF-based approach for multimodal learning. Concretely, given a video recording of an audio-visual scene, the task is to synthesize new videos with spatial audios along arbitrary novel camera trajectories in that scene. We propose an acoustic-aware audio generation module that integrates prior knowledge of audio propagation into NeRF, in which we "},"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":"2302.02088","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-04T04:17:19Z","cross_cats_sorted":["cs.GR","cs.SD","eess.AS"],"title_canon_sha256":"d920266df61c4c95c365c0be250fb65b462404f63576789aab0bac343c50f32f","abstract_canon_sha256":"0ccdc69fbb1e23fb3a11ac4a40027532b0b847c3a25dfb4b566a393edb4e6eb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:58.753018Z","signature_b64":"7i92xkYC3iCEiw4hSYpUwzB1tGkNZir+SRqIQgOy9dTiYv5FvPEZNoW0YcLLEXHTdsrPN8u3vQtTgqNrfgQ1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"700faa9ac295a28900221486b89b378d7e800ad039e33b885b8a7b9bc6e9c6f7","last_reissued_at":"2026-07-05T07:00:58.752459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:58.752459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Anurag Kumar, Chao Huang, Chenliang Xu, Susan Liang, Yapeng Tian","submitted_at":"2023-02-04T04:17:19Z","abstract_excerpt":"Can machines recording an audio-visual scene produce realistic, matching audio-visual experiences at novel positions and novel view directions? We answer it by studying a new task -- real-world audio-visual scene synthesis -- and a first-of-its-kind NeRF-based approach for multimodal learning. Concretely, given a video recording of an audio-visual scene, the task is to synthesize new videos with spatial audios along arbitrary novel camera trajectories in that scene. We propose an acoustic-aware audio generation module that integrates prior knowledge of audio propagation into NeRF, in which we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02088","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/2302.02088/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":"2302.02088","created_at":"2026-07-05T07:00:58.752524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02088v3","created_at":"2026-07-05T07:00:58.752524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02088","created_at":"2026-07-05T07:00:58.752524+00:00"},{"alias_kind":"pith_short_12","alias_value":"OAH2VGWCSWRI","created_at":"2026-07-05T07:00:58.752524+00:00"},{"alias_kind":"pith_short_16","alias_value":"OAH2VGWCSWRISABC","created_at":"2026-07-05T07:00:58.752524+00:00"},{"alias_kind":"pith_short_8","alias_value":"OAH2VGWC","created_at":"2026-07-05T07:00:58.752524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21119","citing_title":"Materialistic RIR: Material Conditioned Realistic RIR Generation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OAH2VGWCSWRISABCCSDLRGZXRV","json":"https://pith.science/pith/OAH2VGWCSWRISABCCSDLRGZXRV.json","graph_json":"https://pith.science/api/pith-number/OAH2VGWCSWRISABCCSDLRGZXRV/graph.json","events_json":"https://pith.science/api/pith-number/OAH2VGWCSWRISABCCSDLRGZXRV/events.json","paper":"https://pith.science/paper/OAH2VGWC"},"agent_actions":{"view_html":"https://pith.science/pith/OAH2VGWCSWRISABCCSDLRGZXRV","download_json":"https://pith.science/pith/OAH2VGWCSWRISABCCSDLRGZXRV.json","view_paper":"https://pith.science/paper/OAH2VGWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02088&json=true","fetch_graph":"https://pith.science/api/pith-number/OAH2VGWCSWRISABCCSDLRGZXRV/graph.json","fetch_events":"https://pith.science/api/pith-number/OAH2VGWCSWRISABCCSDLRGZXRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OAH2VGWCSWRISABCCSDLRGZXRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OAH2VGWCSWRISABCCSDLRGZXRV/action/storage_attestation","attest_author":"https://pith.science/pith/OAH2VGWCSWRISABCCSDLRGZXRV/action/author_attestation","sign_citation":"https://pith.science/pith/OAH2VGWCSWRISABCCSDLRGZXRV/action/citation_signature","submit_replication":"https://pith.science/pith/OAH2VGWCSWRISABCCSDLRGZXRV/action/replication_record"}},"created_at":"2026-07-05T07:00:58.752524+00:00","updated_at":"2026-07-05T07:00:58.752524+00:00"}