{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5WXYL77Y3OU3K2PYQWF2GPLJJF","short_pith_number":"pith:5WXYL77Y","schema_version":"1.0","canonical_sha256":"edaf85fff8dba9b569f8858ba33d694950f878e6b4ac71d7668430359ee6ba84","source":{"kind":"arxiv","id":"2203.07677","version":2},"attestation_state":"computed","paper":{"title":"Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Caihua Kong, Longgang Dai, Pengpeng Li, Xiang Chen, Yufeng Huang, Yufeng Li, Zhentao Fan, Zhuoran Zheng","submitted_at":"2022-03-15T06:45:03Z","abstract_excerpt":"We offer a practical unpaired learning based image dehazing network from an unpaired set of clear and hazy images. This paper provides a new perspective to treat image dehazing as a two-class separated factor disentanglement task, i.e, the task-relevant factor of clear image reconstruction and the task-irrelevant factor of haze-relevant distribution. To achieve the disentanglement of these two-class factors in deep feature space, contrastive learning is introduced into a CycleGAN framework to learn disentangled representations by guiding the generated images to be associated with latent factor"},"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":"2203.07677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2022-03-15T06:45:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"04c93bff5ff36ee5b5c7639781faad102559e0ab02ddb812db29fb6a4a6b816d","abstract_canon_sha256":"9d600fd949425db534dd431b193fb399ec3af2fdc58f20b54ce64037e331ef52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:32.552646Z","signature_b64":"29Wr4+VoeHOXz0Y5ns1yHI8KV1i8kpi3pnE02jczj3eL0ERlxttVx0J4ekqXLZtr/j7TqtGSCZwlsrh1Xy3FCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edaf85fff8dba9b569f8858ba33d694950f878e6b4ac71d7668430359ee6ba84","last_reissued_at":"2026-07-05T04:39:32.552164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:32.552164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Caihua Kong, Longgang Dai, Pengpeng Li, Xiang Chen, Yufeng Huang, Yufeng Li, Zhentao Fan, Zhuoran Zheng","submitted_at":"2022-03-15T06:45:03Z","abstract_excerpt":"We offer a practical unpaired learning based image dehazing network from an unpaired set of clear and hazy images. This paper provides a new perspective to treat image dehazing as a two-class separated factor disentanglement task, i.e, the task-relevant factor of clear image reconstruction and the task-irrelevant factor of haze-relevant distribution. To achieve the disentanglement of these two-class factors in deep feature space, contrastive learning is introduced into a CycleGAN framework to learn disentangled representations by guiding the generated images to be associated with latent factor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07677","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/2203.07677/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":"2203.07677","created_at":"2026-07-05T04:39:32.552221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07677v2","created_at":"2026-07-05T04:39:32.552221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07677","created_at":"2026-07-05T04:39:32.552221+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WXYL77Y3OU3","created_at":"2026-07-05T04:39:32.552221+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WXYL77Y3OU3K2PY","created_at":"2026-07-05T04:39:32.552221+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WXYL77Y","created_at":"2026-07-05T04:39:32.552221+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/5WXYL77Y3OU3K2PYQWF2GPLJJF","json":"https://pith.science/pith/5WXYL77Y3OU3K2PYQWF2GPLJJF.json","graph_json":"https://pith.science/api/pith-number/5WXYL77Y3OU3K2PYQWF2GPLJJF/graph.json","events_json":"https://pith.science/api/pith-number/5WXYL77Y3OU3K2PYQWF2GPLJJF/events.json","paper":"https://pith.science/paper/5WXYL77Y"},"agent_actions":{"view_html":"https://pith.science/pith/5WXYL77Y3OU3K2PYQWF2GPLJJF","download_json":"https://pith.science/pith/5WXYL77Y3OU3K2PYQWF2GPLJJF.json","view_paper":"https://pith.science/paper/5WXYL77Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07677&json=true","fetch_graph":"https://pith.science/api/pith-number/5WXYL77Y3OU3K2PYQWF2GPLJJF/graph.json","fetch_events":"https://pith.science/api/pith-number/5WXYL77Y3OU3K2PYQWF2GPLJJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WXYL77Y3OU3K2PYQWF2GPLJJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WXYL77Y3OU3K2PYQWF2GPLJJF/action/storage_attestation","attest_author":"https://pith.science/pith/5WXYL77Y3OU3K2PYQWF2GPLJJF/action/author_attestation","sign_citation":"https://pith.science/pith/5WXYL77Y3OU3K2PYQWF2GPLJJF/action/citation_signature","submit_replication":"https://pith.science/pith/5WXYL77Y3OU3K2PYQWF2GPLJJF/action/replication_record"}},"created_at":"2026-07-05T04:39:32.552221+00:00","updated_at":"2026-07-05T04:39:32.552221+00:00"}