{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CBVNIR747B564UTIDR2EJUFLD7","short_pith_number":"pith:CBVNIR74","schema_version":"1.0","canonical_sha256":"106ad447fcf87bee52681c7444d0ab1ffd2c81b5caa8962173bce3027df251f6","source":{"kind":"arxiv","id":"2108.13697","version":1},"attestation_state":"computed","paper":{"title":"Attention-based Multi-Reference Learning for Image Super-Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adrian Hilton, Marco Pesavento, Marco Volino","submitted_at":"2021-08-31T09:12:26Z","abstract_excerpt":"This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar texture from multiple reference images to the super-resolution output whilst maintaining spatial coherence. The use of multiple reference images together with attention-based sampling is demonstrated to achieve significantly improved performance over state-of-the-art reference super-resolution approaches on multiple benchmark datasets. Reference super-resolution approaches have recently been proposed to overcome the ill-"},"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":"2108.13697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-31T09:12:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c0b33e26df5495906ffeb8f971f0db86faf89f256630d310ebe1ba087171439f","abstract_canon_sha256":"0b945203aa4c15abd9cb1e768fc3667e79055a0521549d291ab728e942fd02ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:10:16.958599Z","signature_b64":"nj7BRMeybtrq3x/gowahNeymn0leJmJILi0cby1ibttBxNT/cPkzrq+dymP9mrDQ55TziazjkLl/KS8WcrF4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"106ad447fcf87bee52681c7444d0ab1ffd2c81b5caa8962173bce3027df251f6","last_reissued_at":"2026-07-05T03:10:16.958196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:10:16.958196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-based Multi-Reference Learning for Image Super-Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adrian Hilton, Marco Pesavento, Marco Volino","submitted_at":"2021-08-31T09:12:26Z","abstract_excerpt":"This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar texture from multiple reference images to the super-resolution output whilst maintaining spatial coherence. The use of multiple reference images together with attention-based sampling is demonstrated to achieve significantly improved performance over state-of-the-art reference super-resolution approaches on multiple benchmark datasets. Reference super-resolution approaches have recently been proposed to overcome the ill-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13697","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/2108.13697/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":"2108.13697","created_at":"2026-07-05T03:10:16.958253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.13697v1","created_at":"2026-07-05T03:10:16.958253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13697","created_at":"2026-07-05T03:10:16.958253+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBVNIR747B56","created_at":"2026-07-05T03:10:16.958253+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBVNIR747B564UTI","created_at":"2026-07-05T03:10:16.958253+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBVNIR74","created_at":"2026-07-05T03:10:16.958253+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13756","citing_title":"UltraZoom: Generating Gigapixel Images from Regular Photos","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBVNIR747B564UTIDR2EJUFLD7","json":"https://pith.science/pith/CBVNIR747B564UTIDR2EJUFLD7.json","graph_json":"https://pith.science/api/pith-number/CBVNIR747B564UTIDR2EJUFLD7/graph.json","events_json":"https://pith.science/api/pith-number/CBVNIR747B564UTIDR2EJUFLD7/events.json","paper":"https://pith.science/paper/CBVNIR74"},"agent_actions":{"view_html":"https://pith.science/pith/CBVNIR747B564UTIDR2EJUFLD7","download_json":"https://pith.science/pith/CBVNIR747B564UTIDR2EJUFLD7.json","view_paper":"https://pith.science/paper/CBVNIR74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.13697&json=true","fetch_graph":"https://pith.science/api/pith-number/CBVNIR747B564UTIDR2EJUFLD7/graph.json","fetch_events":"https://pith.science/api/pith-number/CBVNIR747B564UTIDR2EJUFLD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBVNIR747B564UTIDR2EJUFLD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBVNIR747B564UTIDR2EJUFLD7/action/storage_attestation","attest_author":"https://pith.science/pith/CBVNIR747B564UTIDR2EJUFLD7/action/author_attestation","sign_citation":"https://pith.science/pith/CBVNIR747B564UTIDR2EJUFLD7/action/citation_signature","submit_replication":"https://pith.science/pith/CBVNIR747B564UTIDR2EJUFLD7/action/replication_record"}},"created_at":"2026-07-05T03:10:16.958253+00:00","updated_at":"2026-07-05T03:10:16.958253+00:00"}