{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DTXVMAUMAJ6UIDZBP2GAAAWCYA","short_pith_number":"pith:DTXVMAUM","schema_version":"1.0","canonical_sha256":"1cef56028c027d440f217e8c0002c2c01223e24e17aabda224346b4b9285f7de","source":{"kind":"arxiv","id":"2402.04930","version":2},"attestation_state":"computed","paper":{"title":"Blue noise for diffusion models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cengiz \\\"Oztireli, Christian Theobalt, Corentin Sala\\\"un, Cristina Vasconcelos, Gurprit Singh, Xingchang Huang","submitted_at":"2024-02-07T14:59:25Z","abstract_excerpt":"Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed by the denoising network. Despite the diverse applications of correlated noise in computer graphics, its potential for improving the training process has been underexplored. In this paper, we introduce a novel and general class of diffusion models taking correlated noise within and across images into account. More specifically, we propose a time-varying noise model to incorporate correlated noise into the training pro"},"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":"2402.04930","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T14:59:25Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"7ca5df927449df3dcdb5c1acc21cd27716504de06697f5ae08383215ed3bcce5","abstract_canon_sha256":"0818a1e60e1230a56dde2ad72be016f28438036913c7467f1a93c4a11b3502d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:40.905708Z","signature_b64":"5fZN5Zcf6LfQCUztm9QumY1YYq9CL5hcCwZhkFg9nVw7o9zFal7BxUfx/417lKQz6cOfsN0OVOKo4LZL1PM0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cef56028c027d440f217e8c0002c2c01223e24e17aabda224346b4b9285f7de","last_reissued_at":"2026-07-05T08:14:40.905277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:40.905277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blue noise for diffusion models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cengiz \\\"Oztireli, Christian Theobalt, Corentin Sala\\\"un, Cristina Vasconcelos, Gurprit Singh, Xingchang Huang","submitted_at":"2024-02-07T14:59:25Z","abstract_excerpt":"Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed by the denoising network. Despite the diverse applications of correlated noise in computer graphics, its potential for improving the training process has been underexplored. In this paper, we introduce a novel and general class of diffusion models taking correlated noise within and across images into account. More specifically, we propose a time-varying noise model to incorporate correlated noise into the training pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04930","kind":"arxiv","version":2},"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/2402.04930/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":"2402.04930","created_at":"2026-07-05T08:14:40.905338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04930v2","created_at":"2026-07-05T08:14:40.905338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04930","created_at":"2026-07-05T08:14:40.905338+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTXVMAUMAJ6U","created_at":"2026-07-05T08:14:40.905338+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTXVMAUMAJ6UIDZB","created_at":"2026-07-05T08:14:40.905338+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTXVMAUM","created_at":"2026-07-05T08:14:40.905338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23540","citing_title":"Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DTXVMAUMAJ6UIDZBP2GAAAWCYA","json":"https://pith.science/pith/DTXVMAUMAJ6UIDZBP2GAAAWCYA.json","graph_json":"https://pith.science/api/pith-number/DTXVMAUMAJ6UIDZBP2GAAAWCYA/graph.json","events_json":"https://pith.science/api/pith-number/DTXVMAUMAJ6UIDZBP2GAAAWCYA/events.json","paper":"https://pith.science/paper/DTXVMAUM"},"agent_actions":{"view_html":"https://pith.science/pith/DTXVMAUMAJ6UIDZBP2GAAAWCYA","download_json":"https://pith.science/pith/DTXVMAUMAJ6UIDZBP2GAAAWCYA.json","view_paper":"https://pith.science/paper/DTXVMAUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04930&json=true","fetch_graph":"https://pith.science/api/pith-number/DTXVMAUMAJ6UIDZBP2GAAAWCYA/graph.json","fetch_events":"https://pith.science/api/pith-number/DTXVMAUMAJ6UIDZBP2GAAAWCYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTXVMAUMAJ6UIDZBP2GAAAWCYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTXVMAUMAJ6UIDZBP2GAAAWCYA/action/storage_attestation","attest_author":"https://pith.science/pith/DTXVMAUMAJ6UIDZBP2GAAAWCYA/action/author_attestation","sign_citation":"https://pith.science/pith/DTXVMAUMAJ6UIDZBP2GAAAWCYA/action/citation_signature","submit_replication":"https://pith.science/pith/DTXVMAUMAJ6UIDZBP2GAAAWCYA/action/replication_record"}},"created_at":"2026-07-05T08:14:40.905338+00:00","updated_at":"2026-07-05T08:14:40.905338+00:00"}