{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ESM23NZI4BJECWBDMVVKDA6FKI","short_pith_number":"pith:ESM23NZI","schema_version":"1.0","canonical_sha256":"2499adb728e052415823656aa183c552387750e70b26e07d315810f097e167f4","source":{"kind":"arxiv","id":"2101.05796","version":2},"attestation_state":"computed","paper":{"title":"DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Andreas Lugmayr, Luc Van Gool, Martin Danelljan, Radu Timofte, Valentin Wolf","submitted_at":"2021-01-14T18:58:01Z","abstract_excerpt":"The difficulty of obtaining paired data remains a major bottleneck for learning image restoration and enhancement models for real-world applications. Current strategies aim to synthesize realistic training data by modeling noise and degradations that appear in real-world settings. We propose DeFlow, a method for learning stochastic image degradations from unpaired data. Our approach is based on a novel unpaired learning formulation for conditional normalizing flows. We model the degradation process in the latent space of a shared flow encoder-decoder network. This allows us to learn the condit"},"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":"2101.05796","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-14T18:58:01Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"7bc04d1b6c0fca64e25b7d25c7a4d2bf6d3e5ad774de3dd988dce7b268037704","abstract_canon_sha256":"36af0e47086aff42c81153a345b9eccac243ecfc468032f07e42994c9a354c63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:53.167231Z","signature_b64":"CAOD9JViRtZ2Njque/YUPNFrCKHr8MeyqB7Rh09m9AOz3jj96rPdtV2TO10Qvoj4HeNhyYinK1AoB9LSCZW4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2499adb728e052415823656aa183c552387750e70b26e07d315810f097e167f4","last_reissued_at":"2026-07-05T03:14:53.166818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:53.166818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Andreas Lugmayr, Luc Van Gool, Martin Danelljan, Radu Timofte, Valentin Wolf","submitted_at":"2021-01-14T18:58:01Z","abstract_excerpt":"The difficulty of obtaining paired data remains a major bottleneck for learning image restoration and enhancement models for real-world applications. Current strategies aim to synthesize realistic training data by modeling noise and degradations that appear in real-world settings. We propose DeFlow, a method for learning stochastic image degradations from unpaired data. Our approach is based on a novel unpaired learning formulation for conditional normalizing flows. We model the degradation process in the latent space of a shared flow encoder-decoder network. This allows us to learn the condit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.05796","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/2101.05796/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":"2101.05796","created_at":"2026-07-05T03:14:53.166874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.05796v2","created_at":"2026-07-05T03:14:53.166874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.05796","created_at":"2026-07-05T03:14:53.166874+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESM23NZI4BJE","created_at":"2026-07-05T03:14:53.166874+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESM23NZI4BJECWBD","created_at":"2026-07-05T03:14:53.166874+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESM23NZI","created_at":"2026-07-05T03:14:53.166874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESM23NZI4BJECWBDMVVKDA6FKI","json":"https://pith.science/pith/ESM23NZI4BJECWBDMVVKDA6FKI.json","graph_json":"https://pith.science/api/pith-number/ESM23NZI4BJECWBDMVVKDA6FKI/graph.json","events_json":"https://pith.science/api/pith-number/ESM23NZI4BJECWBDMVVKDA6FKI/events.json","paper":"https://pith.science/paper/ESM23NZI"},"agent_actions":{"view_html":"https://pith.science/pith/ESM23NZI4BJECWBDMVVKDA6FKI","download_json":"https://pith.science/pith/ESM23NZI4BJECWBDMVVKDA6FKI.json","view_paper":"https://pith.science/paper/ESM23NZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.05796&json=true","fetch_graph":"https://pith.science/api/pith-number/ESM23NZI4BJECWBDMVVKDA6FKI/graph.json","fetch_events":"https://pith.science/api/pith-number/ESM23NZI4BJECWBDMVVKDA6FKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESM23NZI4BJECWBDMVVKDA6FKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESM23NZI4BJECWBDMVVKDA6FKI/action/storage_attestation","attest_author":"https://pith.science/pith/ESM23NZI4BJECWBDMVVKDA6FKI/action/author_attestation","sign_citation":"https://pith.science/pith/ESM23NZI4BJECWBDMVVKDA6FKI/action/citation_signature","submit_replication":"https://pith.science/pith/ESM23NZI4BJECWBDMVVKDA6FKI/action/replication_record"}},"created_at":"2026-07-05T03:14:53.166874+00:00","updated_at":"2026-07-05T03:14:53.166874+00:00"}