{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D74YFFNTL5PC7FDBYBWOSXWTQL","short_pith_number":"pith:D74YFFNT","schema_version":"1.0","canonical_sha256":"1ff98295b35f5e2f9461c06ce95ed382fb05c8be9929f87a55bbe830f034c1d4","source":{"kind":"arxiv","id":"2410.15385","version":2},"attestation_state":"computed","paper":{"title":"LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaibo Huang, Ran He, Yuang Ai","submitted_at":"2024-10-20T13:00:24Z","abstract_excerpt":"Prompt-based all-in-one image restoration (IR) frameworks have achieved remarkable performance by incorporating degradation-specific information into prompt modules. Nevertheless, handling the complex and diverse degradations encountered in real-world scenarios remains a significant challenge. To tackle this, we propose LoRA-IR, a flexible framework that dynamically leverages compact low-rank experts to facilitate efficient all-in-one image restoration. Specifically, LoRA-IR consists of two training stages: degradation-guided pre-training and parameter-efficient fine-tuning. In the pre-trainin"},"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":"2410.15385","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-20T13:00:24Z","cross_cats_sorted":[],"title_canon_sha256":"5b5a07cb2c1d01508d45ba6926986e3f7c73669c5da6c79b8115a4b0c9e7fa39","abstract_canon_sha256":"c6c7ca487ec58930d5e0edba6220f87359ccb981c8e8c0d12006e3f1d5d61d07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:15.377217Z","signature_b64":"gKrlUXpPH49IQ8U5Fyo6k4KUO5lhmT/MGooNk1+HHy0Dv4r9rkXs+bsEhcWcDOrKFkTu1iRmCw+UuhRScMuKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ff98295b35f5e2f9461c06ce95ed382fb05c8be9929f87a55bbe830f034c1d4","last_reissued_at":"2026-07-05T09:36:15.376727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:15.376727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaibo Huang, Ran He, Yuang Ai","submitted_at":"2024-10-20T13:00:24Z","abstract_excerpt":"Prompt-based all-in-one image restoration (IR) frameworks have achieved remarkable performance by incorporating degradation-specific information into prompt modules. Nevertheless, handling the complex and diverse degradations encountered in real-world scenarios remains a significant challenge. To tackle this, we propose LoRA-IR, a flexible framework that dynamically leverages compact low-rank experts to facilitate efficient all-in-one image restoration. Specifically, LoRA-IR consists of two training stages: degradation-guided pre-training and parameter-efficient fine-tuning. In the pre-trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15385","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/2410.15385/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":"2410.15385","created_at":"2026-07-05T09:36:15.376791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15385v2","created_at":"2026-07-05T09:36:15.376791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15385","created_at":"2026-07-05T09:36:15.376791+00:00"},{"alias_kind":"pith_short_12","alias_value":"D74YFFNTL5PC","created_at":"2026-07-05T09:36:15.376791+00:00"},{"alias_kind":"pith_short_16","alias_value":"D74YFFNTL5PC7FDB","created_at":"2026-07-05T09:36:15.376791+00:00"},{"alias_kind":"pith_short_8","alias_value":"D74YFFNT","created_at":"2026-07-05T09:36:15.376791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02742","citing_title":"Task-Guided Prompting for Unified Remote Sensing Image Restoration","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12006","citing_title":"Robust Promptable Video Object Segmentation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06127","citing_title":"Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D74YFFNTL5PC7FDBYBWOSXWTQL","json":"https://pith.science/pith/D74YFFNTL5PC7FDBYBWOSXWTQL.json","graph_json":"https://pith.science/api/pith-number/D74YFFNTL5PC7FDBYBWOSXWTQL/graph.json","events_json":"https://pith.science/api/pith-number/D74YFFNTL5PC7FDBYBWOSXWTQL/events.json","paper":"https://pith.science/paper/D74YFFNT"},"agent_actions":{"view_html":"https://pith.science/pith/D74YFFNTL5PC7FDBYBWOSXWTQL","download_json":"https://pith.science/pith/D74YFFNTL5PC7FDBYBWOSXWTQL.json","view_paper":"https://pith.science/paper/D74YFFNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15385&json=true","fetch_graph":"https://pith.science/api/pith-number/D74YFFNTL5PC7FDBYBWOSXWTQL/graph.json","fetch_events":"https://pith.science/api/pith-number/D74YFFNTL5PC7FDBYBWOSXWTQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D74YFFNTL5PC7FDBYBWOSXWTQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D74YFFNTL5PC7FDBYBWOSXWTQL/action/storage_attestation","attest_author":"https://pith.science/pith/D74YFFNTL5PC7FDBYBWOSXWTQL/action/author_attestation","sign_citation":"https://pith.science/pith/D74YFFNTL5PC7FDBYBWOSXWTQL/action/citation_signature","submit_replication":"https://pith.science/pith/D74YFFNTL5PC7FDBYBWOSXWTQL/action/replication_record"}},"created_at":"2026-07-05T09:36:15.376791+00:00","updated_at":"2026-07-05T09:36:15.376791+00:00"}