{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KYQFVDGZUBUUKQQOPUTFVPFCXV","short_pith_number":"pith:KYQFVDGZ","schema_version":"1.0","canonical_sha256":"56205a8cd9a06945420e7d265abca2bd4ea2b270d22ad8c3231b10f47c5feda9","source":{"kind":"arxiv","id":"2205.01871","version":1},"attestation_state":"computed","paper":{"title":"UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu Lee Wang, Haoran Xie, Jing Qin, Mingqiang Wei, Wenhan Yang, Xuefeng Yan, Yongzhen Wang","submitted_at":"2022-05-04T03:25:13Z","abstract_excerpt":"While the wisdom of training an image dehazing model on synthetic hazy data can alleviate the difficulty of collecting real-world hazy/clean image pairs, it brings the well-known domain shift problem. From a different yet new perspective, this paper explores contrastive learning with an adversarial training effort to leverage unpaired real-world hazy and clean images, thus bridging the gap between synthetic and real-world haze is avoided. We propose an effective unsupervised contrastive learning paradigm for image dehazing, dubbed UCL-Dehaze. Unpaired real-world clean and hazy images are easil"},"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":"2205.01871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-04T03:25:13Z","cross_cats_sorted":[],"title_canon_sha256":"899a08585bdb9822786cf7c02282cfecdcac68bc16ef479e4ef810819b8b81e0","abstract_canon_sha256":"69ab40f05b274e09ac61190a9fa94009e5aa098f66e9bf242e6eaa4b56c206a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:23.097156Z","signature_b64":"UUTbevenIPRkX0UKzGoKXNUooBAS7Zkz+LImZI/w86nmV6MCkOoDUxh+ee9P1LYWTdJ4xuV63kmWAw6A4guuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56205a8cd9a06945420e7d265abca2bd4ea2b270d22ad8c3231b10f47c5feda9","last_reissued_at":"2026-07-05T04:20:23.096681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:23.096681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu Lee Wang, Haoran Xie, Jing Qin, Mingqiang Wei, Wenhan Yang, Xuefeng Yan, Yongzhen Wang","submitted_at":"2022-05-04T03:25:13Z","abstract_excerpt":"While the wisdom of training an image dehazing model on synthetic hazy data can alleviate the difficulty of collecting real-world hazy/clean image pairs, it brings the well-known domain shift problem. From a different yet new perspective, this paper explores contrastive learning with an adversarial training effort to leverage unpaired real-world hazy and clean images, thus bridging the gap between synthetic and real-world haze is avoided. We propose an effective unsupervised contrastive learning paradigm for image dehazing, dubbed UCL-Dehaze. Unpaired real-world clean and hazy images are easil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.01871","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/2205.01871/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":"2205.01871","created_at":"2026-07-05T04:20:23.096739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.01871v1","created_at":"2026-07-05T04:20:23.096739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01871","created_at":"2026-07-05T04:20:23.096739+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYQFVDGZUBUU","created_at":"2026-07-05T04:20:23.096739+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYQFVDGZUBUUKQQO","created_at":"2026-07-05T04:20:23.096739+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYQFVDGZ","created_at":"2026-07-05T04:20:23.096739+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10682","citing_title":"Underwater Image Enhancement with Cascaded Contrastive Learning","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYQFVDGZUBUUKQQOPUTFVPFCXV","json":"https://pith.science/pith/KYQFVDGZUBUUKQQOPUTFVPFCXV.json","graph_json":"https://pith.science/api/pith-number/KYQFVDGZUBUUKQQOPUTFVPFCXV/graph.json","events_json":"https://pith.science/api/pith-number/KYQFVDGZUBUUKQQOPUTFVPFCXV/events.json","paper":"https://pith.science/paper/KYQFVDGZ"},"agent_actions":{"view_html":"https://pith.science/pith/KYQFVDGZUBUUKQQOPUTFVPFCXV","download_json":"https://pith.science/pith/KYQFVDGZUBUUKQQOPUTFVPFCXV.json","view_paper":"https://pith.science/paper/KYQFVDGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.01871&json=true","fetch_graph":"https://pith.science/api/pith-number/KYQFVDGZUBUUKQQOPUTFVPFCXV/graph.json","fetch_events":"https://pith.science/api/pith-number/KYQFVDGZUBUUKQQOPUTFVPFCXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYQFVDGZUBUUKQQOPUTFVPFCXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYQFVDGZUBUUKQQOPUTFVPFCXV/action/storage_attestation","attest_author":"https://pith.science/pith/KYQFVDGZUBUUKQQOPUTFVPFCXV/action/author_attestation","sign_citation":"https://pith.science/pith/KYQFVDGZUBUUKQQOPUTFVPFCXV/action/citation_signature","submit_replication":"https://pith.science/pith/KYQFVDGZUBUUKQQOPUTFVPFCXV/action/replication_record"}},"created_at":"2026-07-05T04:20:23.096739+00:00","updated_at":"2026-07-05T04:20:23.096739+00:00"}