{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CBRXIQUDKNGRD776V7FJZUVHEP","short_pith_number":"pith:CBRXIQUD","schema_version":"1.0","canonical_sha256":"1063744283534d11fffeafca9cd2a723c8ad35d11be5553bf9126bf1fb14b840","source":{"kind":"arxiv","id":"2412.06209","version":1},"attestation_state":"computed","paper":{"title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Arda Senocak, Hyunwoo Ha, Kim Sung-Bin, Tae-Hyun Oh","submitted_at":"2024-12-09T05:04:50Z","abstract_excerpt":"How does audio describe the world around us? In this work, we propose a method for generating images of visual scenes from diverse in-the-wild sounds. This cross-modal generation task is challenging due to the significant information gap between auditory and visual signals. We address this challenge by designing a model that aligns audio-visual modalities by enriching audio features with visual information and translating them into the visual latent space. These features are then fed into the pre-trained image generator to produce images. To enhance image quality, we use sound source localizat"},"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":"2412.06209","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T05:04:50Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"0f7900664a9f24005e6a33d92907e98661fddde0c22e4b039143a4528bc281a0","abstract_canon_sha256":"a2f1f7f54e4b5861c6b963e9fd0346bdcba41fd9f9c005cdf0d29aff02fa8c37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:17.177605Z","signature_b64":"fkoql2ac+eAPz9llenaj8jkNCNtzZBKrHgH0EXnEKhoBR2LwuwiBROQDE4yEBTxiJrmgPmoPVOvNdCQ0O9qHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1063744283534d11fffeafca9cd2a723c8ad35d11be5553bf9126bf1fb14b840","last_reissued_at":"2026-07-05T09:46:17.177196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:17.177196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Arda Senocak, Hyunwoo Ha, Kim Sung-Bin, Tae-Hyun Oh","submitted_at":"2024-12-09T05:04:50Z","abstract_excerpt":"How does audio describe the world around us? In this work, we propose a method for generating images of visual scenes from diverse in-the-wild sounds. This cross-modal generation task is challenging due to the significant information gap between auditory and visual signals. We address this challenge by designing a model that aligns audio-visual modalities by enriching audio features with visual information and translating them into the visual latent space. These features are then fed into the pre-trained image generator to produce images. To enhance image quality, we use sound source localizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06209","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/2412.06209/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":"2412.06209","created_at":"2026-07-05T09:46:17.177253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06209v1","created_at":"2026-07-05T09:46:17.177253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06209","created_at":"2026-07-05T09:46:17.177253+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBRXIQUDKNGR","created_at":"2026-07-05T09:46:17.177253+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBRXIQUDKNGRD776","created_at":"2026-07-05T09:46:17.177253+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBRXIQUD","created_at":"2026-07-05T09:46:17.177253+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21761","citing_title":"Learning from Silence and Noise for Visual Sound Source Localization","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBRXIQUDKNGRD776V7FJZUVHEP","json":"https://pith.science/pith/CBRXIQUDKNGRD776V7FJZUVHEP.json","graph_json":"https://pith.science/api/pith-number/CBRXIQUDKNGRD776V7FJZUVHEP/graph.json","events_json":"https://pith.science/api/pith-number/CBRXIQUDKNGRD776V7FJZUVHEP/events.json","paper":"https://pith.science/paper/CBRXIQUD"},"agent_actions":{"view_html":"https://pith.science/pith/CBRXIQUDKNGRD776V7FJZUVHEP","download_json":"https://pith.science/pith/CBRXIQUDKNGRD776V7FJZUVHEP.json","view_paper":"https://pith.science/paper/CBRXIQUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06209&json=true","fetch_graph":"https://pith.science/api/pith-number/CBRXIQUDKNGRD776V7FJZUVHEP/graph.json","fetch_events":"https://pith.science/api/pith-number/CBRXIQUDKNGRD776V7FJZUVHEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBRXIQUDKNGRD776V7FJZUVHEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBRXIQUDKNGRD776V7FJZUVHEP/action/storage_attestation","attest_author":"https://pith.science/pith/CBRXIQUDKNGRD776V7FJZUVHEP/action/author_attestation","sign_citation":"https://pith.science/pith/CBRXIQUDKNGRD776V7FJZUVHEP/action/citation_signature","submit_replication":"https://pith.science/pith/CBRXIQUDKNGRD776V7FJZUVHEP/action/replication_record"}},"created_at":"2026-07-05T09:46:17.177253+00:00","updated_at":"2026-07-05T09:46:17.177253+00:00"}