{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BYDYHOHPNSJAYJXIKQLWAGFOFK","short_pith_number":"pith:BYDYHOHP","schema_version":"1.0","canonical_sha256":"0e0783b8ef6c920c26e854176018ae2a8553f33a110038dc41288433cfb0ed83","source":{"kind":"arxiv","id":"2102.02808","version":2},"attestation_state":"computed","paper":{"title":"Multi-Stage Progressive Image Restoration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Arora, Fahad Shahbaz Khan, Ling Shao, Ming-Hsuan Yang, Munawar Hayat, Salman Khan, Syed Waqas Zamir","submitted_at":"2021-02-04T18:57:07Z","abstract_excerpt":"Image restoration tasks demand a complex balance between spatial details and high-level contextualized information while recovering images. In this paper, we propose a novel synergistic design that can optimally balance these competing goals. Our main proposal is a multi-stage architecture, that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps. Specifically, our model first learns the contextualized features using encoder-decoder architectures and later combines them with a high-resolution branch t"},"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":"2102.02808","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-04T18:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"de1633cbb9fc3bf8aefd068aa843c958a341f1981fa3a8077347dfdef020f21d","abstract_canon_sha256":"f1186f57fed6e261f372c961ac3f5239cfe874ca5a7f178f32dcc2a6e385043e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:23:26.378300Z","signature_b64":"dQ0mcnycCFSUmVPR9EeLiPyDlOpZNpjHxEnSVJlzOTy25DamZ+KKk5SxC6zMVrZj5xRWOdMDoAhGfG/zkrJECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e0783b8ef6c920c26e854176018ae2a8553f33a110038dc41288433cfb0ed83","last_reissued_at":"2026-07-05T02:23:26.377855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:23:26.377855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Stage Progressive Image Restoration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Arora, Fahad Shahbaz Khan, Ling Shao, Ming-Hsuan Yang, Munawar Hayat, Salman Khan, Syed Waqas Zamir","submitted_at":"2021-02-04T18:57:07Z","abstract_excerpt":"Image restoration tasks demand a complex balance between spatial details and high-level contextualized information while recovering images. In this paper, we propose a novel synergistic design that can optimally balance these competing goals. Our main proposal is a multi-stage architecture, that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps. Specifically, our model first learns the contextualized features using encoder-decoder architectures and later combines them with a high-resolution branch t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02808","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/2102.02808/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":"2102.02808","created_at":"2026-07-05T02:23:26.377928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.02808v2","created_at":"2026-07-05T02:23:26.377928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02808","created_at":"2026-07-05T02:23:26.377928+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYDYHOHPNSJA","created_at":"2026-07-05T02:23:26.377928+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYDYHOHPNSJAYJXI","created_at":"2026-07-05T02:23:26.377928+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYDYHOHP","created_at":"2026-07-05T02:23:26.377928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.18403","citing_title":"Efficient Transformer for High Resolution Image Motion Deblurring","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYDYHOHPNSJAYJXIKQLWAGFOFK","json":"https://pith.science/pith/BYDYHOHPNSJAYJXIKQLWAGFOFK.json","graph_json":"https://pith.science/api/pith-number/BYDYHOHPNSJAYJXIKQLWAGFOFK/graph.json","events_json":"https://pith.science/api/pith-number/BYDYHOHPNSJAYJXIKQLWAGFOFK/events.json","paper":"https://pith.science/paper/BYDYHOHP"},"agent_actions":{"view_html":"https://pith.science/pith/BYDYHOHPNSJAYJXIKQLWAGFOFK","download_json":"https://pith.science/pith/BYDYHOHPNSJAYJXIKQLWAGFOFK.json","view_paper":"https://pith.science/paper/BYDYHOHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.02808&json=true","fetch_graph":"https://pith.science/api/pith-number/BYDYHOHPNSJAYJXIKQLWAGFOFK/graph.json","fetch_events":"https://pith.science/api/pith-number/BYDYHOHPNSJAYJXIKQLWAGFOFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYDYHOHPNSJAYJXIKQLWAGFOFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYDYHOHPNSJAYJXIKQLWAGFOFK/action/storage_attestation","attest_author":"https://pith.science/pith/BYDYHOHPNSJAYJXIKQLWAGFOFK/action/author_attestation","sign_citation":"https://pith.science/pith/BYDYHOHPNSJAYJXIKQLWAGFOFK/action/citation_signature","submit_replication":"https://pith.science/pith/BYDYHOHPNSJAYJXIKQLWAGFOFK/action/replication_record"}},"created_at":"2026-07-05T02:23:26.377928+00:00","updated_at":"2026-07-05T02:23:26.377928+00:00"}