{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3H3IIHF3KCFSFAPAY5AUK2PHUO","short_pith_number":"pith:3H3IIHF3","schema_version":"1.0","canonical_sha256":"d9f6841cbb508b2281e0c7414569e7a3b90fad385bda3343be59e634f94bc690","source":{"kind":"arxiv","id":"2410.06551","version":1},"attestation_state":"computed","paper":{"title":"InstantIR: Blind Image Restoration with Instant Generative Reference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Ai, Haofan Wang, Jen-tse Huang, Jen-Yuan Huang, Peng Xing, Qixun Wang, Xu Bai","submitted_at":"2024-10-09T05:15:29Z","abstract_excerpt":"Handling test-time unknown degradation is the major challenge in Blind Image Restoration (BIR), necessitating high model generalization. An effective strategy is to incorporate prior knowledge, either from human input or generative model. In this paper, we introduce Instant-reference Image Restoration (InstantIR), a novel diffusion-based BIR method which dynamically adjusts generation condition during inference. We first extract a compact representation of the input via a pre-trained vision encoder. At each generation step, this representation is used to decode current diffusion latent and ins"},"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":"2410.06551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T05:15:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4899ec66234f8f28607a222f0cc0ccc9b88bf07b615afd983b257af1764039e9","abstract_canon_sha256":"b556e848e18badf13990bd340b7e249316016204db43b3aa584526f59e740898"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:03.921454Z","signature_b64":"qJjqLZwZyr5aYLzAYphfe0V3GOL2+eSBvY6U0NkGVWG9ru6C4yEg1CrIyEC7k51YorRT8oHn0YTDj5IWzLlfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9f6841cbb508b2281e0c7414569e7a3b90fad385bda3343be59e634f94bc690","last_reissued_at":"2026-07-05T09:18:03.920916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:03.920916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstantIR: Blind Image Restoration with Instant Generative Reference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Ai, Haofan Wang, Jen-tse Huang, Jen-Yuan Huang, Peng Xing, Qixun Wang, Xu Bai","submitted_at":"2024-10-09T05:15:29Z","abstract_excerpt":"Handling test-time unknown degradation is the major challenge in Blind Image Restoration (BIR), necessitating high model generalization. An effective strategy is to incorporate prior knowledge, either from human input or generative model. In this paper, we introduce Instant-reference Image Restoration (InstantIR), a novel diffusion-based BIR method which dynamically adjusts generation condition during inference. We first extract a compact representation of the input via a pre-trained vision encoder. At each generation step, this representation is used to decode current diffusion latent and ins"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06551","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/2410.06551/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":"2410.06551","created_at":"2026-07-05T09:18:03.920973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06551v1","created_at":"2026-07-05T09:18:03.920973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06551","created_at":"2026-07-05T09:18:03.920973+00:00"},{"alias_kind":"pith_short_12","alias_value":"3H3IIHF3KCFS","created_at":"2026-07-05T09:18:03.920973+00:00"},{"alias_kind":"pith_short_16","alias_value":"3H3IIHF3KCFSFAPA","created_at":"2026-07-05T09:18:03.920973+00:00"},{"alias_kind":"pith_short_8","alias_value":"3H3IIHF3","created_at":"2026-07-05T09:18:03.920973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.15159","citing_title":"Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3H3IIHF3KCFSFAPAY5AUK2PHUO","json":"https://pith.science/pith/3H3IIHF3KCFSFAPAY5AUK2PHUO.json","graph_json":"https://pith.science/api/pith-number/3H3IIHF3KCFSFAPAY5AUK2PHUO/graph.json","events_json":"https://pith.science/api/pith-number/3H3IIHF3KCFSFAPAY5AUK2PHUO/events.json","paper":"https://pith.science/paper/3H3IIHF3"},"agent_actions":{"view_html":"https://pith.science/pith/3H3IIHF3KCFSFAPAY5AUK2PHUO","download_json":"https://pith.science/pith/3H3IIHF3KCFSFAPAY5AUK2PHUO.json","view_paper":"https://pith.science/paper/3H3IIHF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06551&json=true","fetch_graph":"https://pith.science/api/pith-number/3H3IIHF3KCFSFAPAY5AUK2PHUO/graph.json","fetch_events":"https://pith.science/api/pith-number/3H3IIHF3KCFSFAPAY5AUK2PHUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3H3IIHF3KCFSFAPAY5AUK2PHUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3H3IIHF3KCFSFAPAY5AUK2PHUO/action/storage_attestation","attest_author":"https://pith.science/pith/3H3IIHF3KCFSFAPAY5AUK2PHUO/action/author_attestation","sign_citation":"https://pith.science/pith/3H3IIHF3KCFSFAPAY5AUK2PHUO/action/citation_signature","submit_replication":"https://pith.science/pith/3H3IIHF3KCFSFAPAY5AUK2PHUO/action/replication_record"}},"created_at":"2026-07-05T09:18:03.920973+00:00","updated_at":"2026-07-05T09:18:03.920973+00:00"}