{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AYB2DD2A6FRSDVNLCXV6VF35DX","short_pith_number":"pith:AYB2DD2A","schema_version":"1.0","canonical_sha256":"0603a18f40f16321d5ab15ebea977d1dfe8a4c34c0449a0ccb198a8890d744b2","source":{"kind":"arxiv","id":"2210.06965","version":2},"attestation_state":"computed","paper":{"title":"CUF: Continuous Upsampling Filters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrea Tagliasacchi, Cengiz Oztireli, Cristina Vasconcelos, Kevin Swersky, Mark Matthews, Milad Hashemi","submitted_at":"2022-10-13T12:45:51Z","abstract_excerpt":"Neural fields have rapidly been adopted for representing 3D signals, but their application to more classical 2D image-processing has been relatively limited. In this paper, we consider one of the most important operations in image processing: upsampling. In deep learning, learnable upsampling layers have extensively been used for single image super-resolution. We propose to parameterize upsampling kernels as neural fields. This parameterization leads to a compact architecture that obtains a 40-fold reduction in the number of parameters when compared with competing arbitrary-scale super-resolut"},"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":"2210.06965","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T12:45:51Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"170a6a5c86e139c163b3842de7fe3285695b45876154f71a111e376c843ec9b0","abstract_canon_sha256":"9499630ac375bd780cfc7505a3783eda46b466616b6a533e261b6a52ab832177"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:31.401760Z","signature_b64":"PEKRqodAnBrTCklfJrf0MpOBwoLAtmsSKnYUS+IKkJ5JafGctcmNo1lrOw9YvYpE+yubn1n0S8ZOXtkuKcjCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0603a18f40f16321d5ab15ebea977d1dfe8a4c34c0449a0ccb198a8890d744b2","last_reissued_at":"2026-07-05T05:08:31.401405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:31.401405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CUF: Continuous Upsampling Filters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrea Tagliasacchi, Cengiz Oztireli, Cristina Vasconcelos, Kevin Swersky, Mark Matthews, Milad Hashemi","submitted_at":"2022-10-13T12:45:51Z","abstract_excerpt":"Neural fields have rapidly been adopted for representing 3D signals, but their application to more classical 2D image-processing has been relatively limited. In this paper, we consider one of the most important operations in image processing: upsampling. In deep learning, learnable upsampling layers have extensively been used for single image super-resolution. We propose to parameterize upsampling kernels as neural fields. This parameterization leads to a compact architecture that obtains a 40-fold reduction in the number of parameters when compared with competing arbitrary-scale super-resolut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06965","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/2210.06965/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":"2210.06965","created_at":"2026-07-05T05:08:31.401472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.06965v2","created_at":"2026-07-05T05:08:31.401472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06965","created_at":"2026-07-05T05:08:31.401472+00:00"},{"alias_kind":"pith_short_12","alias_value":"AYB2DD2A6FRS","created_at":"2026-07-05T05:08:31.401472+00:00"},{"alias_kind":"pith_short_16","alias_value":"AYB2DD2A6FRSDVNL","created_at":"2026-07-05T05:08:31.401472+00:00"},{"alias_kind":"pith_short_8","alias_value":"AYB2DD2A","created_at":"2026-07-05T05:08:31.401472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AYB2DD2A6FRSDVNLCXV6VF35DX","json":"https://pith.science/pith/AYB2DD2A6FRSDVNLCXV6VF35DX.json","graph_json":"https://pith.science/api/pith-number/AYB2DD2A6FRSDVNLCXV6VF35DX/graph.json","events_json":"https://pith.science/api/pith-number/AYB2DD2A6FRSDVNLCXV6VF35DX/events.json","paper":"https://pith.science/paper/AYB2DD2A"},"agent_actions":{"view_html":"https://pith.science/pith/AYB2DD2A6FRSDVNLCXV6VF35DX","download_json":"https://pith.science/pith/AYB2DD2A6FRSDVNLCXV6VF35DX.json","view_paper":"https://pith.science/paper/AYB2DD2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.06965&json=true","fetch_graph":"https://pith.science/api/pith-number/AYB2DD2A6FRSDVNLCXV6VF35DX/graph.json","fetch_events":"https://pith.science/api/pith-number/AYB2DD2A6FRSDVNLCXV6VF35DX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AYB2DD2A6FRSDVNLCXV6VF35DX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AYB2DD2A6FRSDVNLCXV6VF35DX/action/storage_attestation","attest_author":"https://pith.science/pith/AYB2DD2A6FRSDVNLCXV6VF35DX/action/author_attestation","sign_citation":"https://pith.science/pith/AYB2DD2A6FRSDVNLCXV6VF35DX/action/citation_signature","submit_replication":"https://pith.science/pith/AYB2DD2A6FRSDVNLCXV6VF35DX/action/replication_record"}},"created_at":"2026-07-05T05:08:31.401472+00:00","updated_at":"2026-07-05T05:08:31.401472+00:00"}