{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GH3BFFKMN24MHXP24QG4SC7LDI","short_pith_number":"pith:GH3BFFKM","schema_version":"1.0","canonical_sha256":"31f612954c6eb8c3ddfae40dc90beb1a300d9ce8596bd71b68f44a08b6eced3e","source":{"kind":"arxiv","id":"2108.05054","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun-pyo Hong, Seo-Won Ji, Seung-Won Jung, Sung-Jea Ko, Sung-Jin Cho","submitted_at":"2021-08-11T06:37:01Z","abstract_excerpt":"Coarse-to-fine strategies have been extensively used for the architecture design of single image deblurring networks. Conventional methods typically stack sub-networks with multi-scale input images and gradually improve sharpness of images from the bottom sub-network to the top sub-network, yielding inevitably high computational costs. Toward a fast and accurate deblurring network design, we revisit the coarse-to-fine strategy and present a multi-input multi-output U-net (MIMO-UNet). The MIMO-UNet has three distinct features. First, the single encoder of the MIMO-UNet takes multi-scale input i"},"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":"2108.05054","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-11T06:37:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f4a2ff89073a3229db9d7d864b723621e1c695a3275db3d5564da4202165757c","abstract_canon_sha256":"1b390d394956f5984dec0c228cb734a090c0fdcaaa9b67db4c9666576e5e8e3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:56.573015Z","signature_b64":"+iAAqGaMaJJJNe7uaDJv9lAwi4hxEpeCOf75WPB/8udSEf638FkAEgk2amgaLOJ5ltPGtqKnnXRS2pP76jcwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31f612954c6eb8c3ddfae40dc90beb1a300d9ce8596bd71b68f44a08b6eced3e","last_reissued_at":"2026-07-05T03:14:56.572574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:56.572574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun-pyo Hong, Seo-Won Ji, Seung-Won Jung, Sung-Jea Ko, Sung-Jin Cho","submitted_at":"2021-08-11T06:37:01Z","abstract_excerpt":"Coarse-to-fine strategies have been extensively used for the architecture design of single image deblurring networks. Conventional methods typically stack sub-networks with multi-scale input images and gradually improve sharpness of images from the bottom sub-network to the top sub-network, yielding inevitably high computational costs. Toward a fast and accurate deblurring network design, we revisit the coarse-to-fine strategy and present a multi-input multi-output U-net (MIMO-UNet). The MIMO-UNet has three distinct features. First, the single encoder of the MIMO-UNet takes multi-scale input i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05054","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/2108.05054/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":"2108.05054","created_at":"2026-07-05T03:14:56.572639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.05054v2","created_at":"2026-07-05T03:14:56.572639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05054","created_at":"2026-07-05T03:14:56.572639+00:00"},{"alias_kind":"pith_short_12","alias_value":"GH3BFFKMN24M","created_at":"2026-07-05T03:14:56.572639+00:00"},{"alias_kind":"pith_short_16","alias_value":"GH3BFFKMN24MHXP2","created_at":"2026-07-05T03:14:56.572639+00:00"},{"alias_kind":"pith_short_8","alias_value":"GH3BFFKM","created_at":"2026-07-05T03:14:56.572639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22128","citing_title":"Real-Time Blind Defocus Deblurring for Earth Observation: The IMAGIN-e Mission Approach","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GH3BFFKMN24MHXP24QG4SC7LDI","json":"https://pith.science/pith/GH3BFFKMN24MHXP24QG4SC7LDI.json","graph_json":"https://pith.science/api/pith-number/GH3BFFKMN24MHXP24QG4SC7LDI/graph.json","events_json":"https://pith.science/api/pith-number/GH3BFFKMN24MHXP24QG4SC7LDI/events.json","paper":"https://pith.science/paper/GH3BFFKM"},"agent_actions":{"view_html":"https://pith.science/pith/GH3BFFKMN24MHXP24QG4SC7LDI","download_json":"https://pith.science/pith/GH3BFFKMN24MHXP24QG4SC7LDI.json","view_paper":"https://pith.science/paper/GH3BFFKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.05054&json=true","fetch_graph":"https://pith.science/api/pith-number/GH3BFFKMN24MHXP24QG4SC7LDI/graph.json","fetch_events":"https://pith.science/api/pith-number/GH3BFFKMN24MHXP24QG4SC7LDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GH3BFFKMN24MHXP24QG4SC7LDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GH3BFFKMN24MHXP24QG4SC7LDI/action/storage_attestation","attest_author":"https://pith.science/pith/GH3BFFKMN24MHXP24QG4SC7LDI/action/author_attestation","sign_citation":"https://pith.science/pith/GH3BFFKMN24MHXP24QG4SC7LDI/action/citation_signature","submit_replication":"https://pith.science/pith/GH3BFFKMN24MHXP24QG4SC7LDI/action/replication_record"}},"created_at":"2026-07-05T03:14:56.572639+00:00","updated_at":"2026-07-05T03:14:56.572639+00:00"}