{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z3UJK7WWIZA7NHIFKA3LOAV4IZ","short_pith_number":"pith:Z3UJK7WW","schema_version":"1.0","canonical_sha256":"cee8957ed64641f69d055036b702bc467dd103f534cdb8feabb0ac49a02dc791","source":{"kind":"arxiv","id":"2406.00721","version":1},"attestation_state":"computed","paper":{"title":"Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjin Yu, Cong Wang, Jie Mu, Wei Wang","submitted_at":"2024-06-02T12:08:16Z","abstract_excerpt":"Patch-level non-local self-similarity is an important property of natural images. However, most existing methods do not consider this property into neural networks for image deraining, thus affecting recovery performance. Motivated by this property, we find that there exists significant patch recurrence property of a rainy image, that is, similar patches tend to recur many times in one image and its multi-scale images and external images. To better model this property for image detaining, we develop a multi-scale graph network with exemplars, called MSGNN, that contains two branches: 1) intern"},"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":"2406.00721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-02T12:08:16Z","cross_cats_sorted":[],"title_canon_sha256":"86eda7ef134db960ff547157f9bbbe65847310b5561d758fb8985b0e7f7b0ba4","abstract_canon_sha256":"850aba9466695fb06e6feef1aec163d8941cbe5cb0e8bd6de96770e95c884420"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:29.922497Z","signature_b64":"QVAMYvrXlQcm6Fpgl7onk1NJ7KEhQDOr15dIAl7dKJ4tgtbgOedOeNbpkz2vtc6K3gZS2hwy9JigGpHQQAXKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cee8957ed64641f69d055036b702bc467dd103f534cdb8feabb0ac49a02dc791","last_reissued_at":"2026-07-05T08:26:29.922086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:29.922086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjin Yu, Cong Wang, Jie Mu, Wei Wang","submitted_at":"2024-06-02T12:08:16Z","abstract_excerpt":"Patch-level non-local self-similarity is an important property of natural images. However, most existing methods do not consider this property into neural networks for image deraining, thus affecting recovery performance. Motivated by this property, we find that there exists significant patch recurrence property of a rainy image, that is, similar patches tend to recur many times in one image and its multi-scale images and external images. To better model this property for image detaining, we develop a multi-scale graph network with exemplars, called MSGNN, that contains two branches: 1) intern"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00721","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/2406.00721/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":"2406.00721","created_at":"2026-07-05T08:26:29.922141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00721v1","created_at":"2026-07-05T08:26:29.922141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00721","created_at":"2026-07-05T08:26:29.922141+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3UJK7WWIZA7","created_at":"2026-07-05T08:26:29.922141+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3UJK7WWIZA7NHIF","created_at":"2026-07-05T08:26:29.922141+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3UJK7WW","created_at":"2026-07-05T08:26:29.922141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19097","citing_title":"DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04630","citing_title":"Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z3UJK7WWIZA7NHIFKA3LOAV4IZ","json":"https://pith.science/pith/Z3UJK7WWIZA7NHIFKA3LOAV4IZ.json","graph_json":"https://pith.science/api/pith-number/Z3UJK7WWIZA7NHIFKA3LOAV4IZ/graph.json","events_json":"https://pith.science/api/pith-number/Z3UJK7WWIZA7NHIFKA3LOAV4IZ/events.json","paper":"https://pith.science/paper/Z3UJK7WW"},"agent_actions":{"view_html":"https://pith.science/pith/Z3UJK7WWIZA7NHIFKA3LOAV4IZ","download_json":"https://pith.science/pith/Z3UJK7WWIZA7NHIFKA3LOAV4IZ.json","view_paper":"https://pith.science/paper/Z3UJK7WW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00721&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3UJK7WWIZA7NHIFKA3LOAV4IZ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3UJK7WWIZA7NHIFKA3LOAV4IZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3UJK7WWIZA7NHIFKA3LOAV4IZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3UJK7WWIZA7NHIFKA3LOAV4IZ/action/storage_attestation","attest_author":"https://pith.science/pith/Z3UJK7WWIZA7NHIFKA3LOAV4IZ/action/author_attestation","sign_citation":"https://pith.science/pith/Z3UJK7WWIZA7NHIFKA3LOAV4IZ/action/citation_signature","submit_replication":"https://pith.science/pith/Z3UJK7WWIZA7NHIFKA3LOAV4IZ/action/replication_record"}},"created_at":"2026-07-05T08:26:29.922141+00:00","updated_at":"2026-07-05T08:26:29.922141+00:00"}