{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ITGZMRS2HMMESOU2ANZBYSSIY3","short_pith_number":"pith:ITGZMRS2","schema_version":"1.0","canonical_sha256":"44cd96465a3b18493a9a03721c4a48c6c1fdbe0ed5ca014873d2b5a305b9ef12","source":{"kind":"arxiv","id":"1803.04189","version":3},"attestation_state":"computed","paper":{"title":"Noise2Noise: Learning Image Restoration without Clean Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jaakko Lehtinen, Jacob Munkberg, Jon Hasselgren, Miika Aittala, Samuli Laine, Tero Karras, Timo Aila","submitted_at":"2018-03-12T11:07:58Z","abstract_excerpt":"We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denoising synthetic Monte Carlo images, and reconstruction of undersampled MRI scans -- all corrupted by different proces"},"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":"1803.04189","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-12T11:07:58Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c3769f7e4cc41c8b1c59ec27694b3d7035f0f3448b872328725b918afcfdaf4d","abstract_canon_sha256":"7562b148900beb1d917e2b19d05b031d22f562cddb2639a48b0ea5fca5cc8636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:12.694158Z","signature_b64":"5YrDIaffv3J9Z6NEc4H+kJ1WcnBYZwWo8UEnJF8bswcR/G27n5f7THZXwOZMy8ClUy0lRgG92JMBmea9N5T9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44cd96465a3b18493a9a03721c4a48c6c1fdbe0ed5ca014873d2b5a305b9ef12","last_reissued_at":"2026-05-18T00:02:12.693561Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:12.693561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise2Noise: Learning Image Restoration without Clean Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jaakko Lehtinen, Jacob Munkberg, Jon Hasselgren, Miika Aittala, Samuli Laine, Tero Karras, Timo Aila","submitted_at":"2018-03-12T11:07:58Z","abstract_excerpt":"We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denoising synthetic Monte Carlo images, and reconstruction of undersampled MRI scans -- all corrupted by different proces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04189","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":""},"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":"1803.04189","created_at":"2026-05-18T00:02:12.693653+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.04189v3","created_at":"2026-05-18T00:02:12.693653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04189","created_at":"2026-05-18T00:02:12.693653+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITGZMRS2HMME","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITGZMRS2HMMESOU2","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITGZMRS2","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"1907.00651","citing_title":"Self-supervised Hyperspectral Image Restoration using Separable Image Prior","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2510.09450","citing_title":"Dynamic Weight-based Temporal Aggregation for Low-light Video Enhancement Under Extreme Noise","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2601.14180","citing_title":"Progressive $\\mathcal{J}$-Invariant Self-supervised Learning for Low-Dose CT Denoising","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2306.16050","citing_title":"Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2407.05087","citing_title":"Linear Attention Based Deep Nonlocal Means Filtering for Multiplicative Noise Removal","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17188","citing_title":"RDDM: A Residual-Driven Drifting Model for High-Fidelity Low-Dose CT Denoising","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2410.00083","citing_title":"A Survey on Diffusion Models for Inverse Problems","ref_index":143,"is_internal_anchor":true},{"citing_arxiv_id":"2601.04775","citing_title":"Towards a Unified Theoretical Framework for Splitting-based Self-Supervised MRI Reconstruction","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2601.14180","citing_title":"Progressive $\\mathcal{J}$-Invariant Self-supervised Learning for Low-Dose CT Denoising","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12567","citing_title":"Pyramid Self-contrastive Learning Framework for Test-time Ultrasound Image Denoising","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26491","citing_title":"TwinSpecNet: Extending APOGEE's chemical reach to low-S/N spectra via empirical paired learning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10583","citing_title":"FrequencyCT: Frequency Domain Self-supervised Low-dose CT Denoising","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01306","citing_title":"Machine Learning Enhanced Laser Spectroscopy for Multi-Species Gas Detection in Complex and Harsh Environments","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05960","citing_title":"A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04484","citing_title":"TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16793","citing_title":"AstroSURE: Learning to Remove Noise from Astronomical Images Without Ground Truth Data","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ITGZMRS2HMMESOU2ANZBYSSIY3","json":"https://pith.science/pith/ITGZMRS2HMMESOU2ANZBYSSIY3.json","graph_json":"https://pith.science/api/pith-number/ITGZMRS2HMMESOU2ANZBYSSIY3/graph.json","events_json":"https://pith.science/api/pith-number/ITGZMRS2HMMESOU2ANZBYSSIY3/events.json","paper":"https://pith.science/paper/ITGZMRS2"},"agent_actions":{"view_html":"https://pith.science/pith/ITGZMRS2HMMESOU2ANZBYSSIY3","download_json":"https://pith.science/pith/ITGZMRS2HMMESOU2ANZBYSSIY3.json","view_paper":"https://pith.science/paper/ITGZMRS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.04189&json=true","fetch_graph":"https://pith.science/api/pith-number/ITGZMRS2HMMESOU2ANZBYSSIY3/graph.json","fetch_events":"https://pith.science/api/pith-number/ITGZMRS2HMMESOU2ANZBYSSIY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITGZMRS2HMMESOU2ANZBYSSIY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITGZMRS2HMMESOU2ANZBYSSIY3/action/storage_attestation","attest_author":"https://pith.science/pith/ITGZMRS2HMMESOU2ANZBYSSIY3/action/author_attestation","sign_citation":"https://pith.science/pith/ITGZMRS2HMMESOU2ANZBYSSIY3/action/citation_signature","submit_replication":"https://pith.science/pith/ITGZMRS2HMMESOU2ANZBYSSIY3/action/replication_record"}},"created_at":"2026-05-18T00:02:12.693653+00:00","updated_at":"2026-05-18T00:02:12.693653+00:00"}