{"paper":{"title":"SF-Flow: Sound field magnitude estimation via flow matching guided by sparse measurements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Flow matching reconstructs 3D sound field magnitudes from sparse microphone measurements up to 1 kHz.","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ege Erdem, Orchisama Das, Shoichi Koyama, Tomohiko Nakamura, Zoran Cvetkovi\\'c","submitted_at":"2026-05-11T11:40:57Z","abstract_excerpt":"Reconstructing a 3D sound field from sparse microphone measurements is a fundamental yet ill-posed problem, which we address through Acoustic Transfer Function (ATF) magnitude estimation. ATF magnitude encapsulates key perceptual and acoustic properties of a physical space with applications in room characterization and correction. Although recent generative paradigms such as Flow Matching (FM) have achieved state-of-the-art performance in speech and music generation, their potential in spatial audio remains underexplored. We propose a novel framework for 3D ATF magnitude reconstruction as a gu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose a novel framework for 3D ATF magnitude reconstruction as a guided generation task, with a 3D U-Net conditioned by a permutation-invariant set encoder. ... Experimental results demonstrate that SF-Flow achieves accurate reconstruction up to 1 kHz, trains substantially faster than the autoencoder baseline, and improves significantly with dataset size.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the flow matching process guided by the permutation-invariant set encoder on a 3D U-Net can reliably recover the underlying acoustic properties from sparse measurements without introducing artifacts or failing at higher frequencies or complex geometries.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SF-Flow applies flow matching with a permutation-invariant set encoder and 3D U-Net to reconstruct ATF magnitudes from sparse inputs, showing accurate results up to 1 kHz with faster training than autoencoder baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Flow matching reconstructs 3D sound field magnitudes from sparse microphone measurements up to 1 kHz.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"af3763c5083558dffa4d86d486754179541b3c2da2a0fb22fd00031a7f1fcaa0"},"source":{"id":"2605.10398","kind":"arxiv","version":2},"verdict":{"id":"e5daa3b4-6315-4d14-82d9-4f94f1954260","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T03:31:56.499306Z","strongest_claim":"We propose a novel framework for 3D ATF magnitude reconstruction as a guided generation task, with a 3D U-Net conditioned by a permutation-invariant set encoder. ... Experimental results demonstrate that SF-Flow achieves accurate reconstruction up to 1 kHz, trains substantially faster than the autoencoder baseline, and improves significantly with dataset size.","one_line_summary":"SF-Flow applies flow matching with a permutation-invariant set encoder and 3D U-Net to reconstruct ATF magnitudes from sparse inputs, showing accurate results up to 1 kHz with faster training than autoencoder baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the flow matching process guided by the permutation-invariant set encoder on a 3D U-Net can reliably recover the underlying acoustic properties from sparse measurements without introducing artifacts or failing at higher frequencies or complex geometries.","pith_extraction_headline":"Flow matching reconstructs 3D sound field magnitudes from sparse microphone measurements up to 1 kHz."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10398/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T06:02:01.033689Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T15:34:13.748723Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:18.212811Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:23:08.366751Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e9b91fce72207ad8794a36744d46851acf14a4004e859eab5f8afed1616a5973"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d7f1ebca740015a34e0407eccce8a9f43ac88502e13a949aae44c66a7b884c3a"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}