{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CP6FGEX5RRXNGTFOGHBHDBKAU3","short_pith_number":"pith:CP6FGEX5","schema_version":"1.0","canonical_sha256":"13fc5312fd8c6ed34cae31c2718540a6cdfc13a11c3512896d3b4393cca012dd","source":{"kind":"arxiv","id":"1811.07945","version":1},"attestation_state":"computed","paper":{"title":"Learning to synthesize: splitting and recombining low and high spatial frequencies for image recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"George Barbastathis, Mo Deng, Shuai Li","submitted_at":"2018-11-19T19:29:20Z","abstract_excerpt":"Deep Neural Network (DNN)-based image reconstruction, despite many successes, often exhibits uneven fidelity between high and low spatial frequency bands. In this paper we propose the Learning Synthesis by DNN (LS-DNN) approach where two DNNs process the low and high spatial frequencies, respectively, and, improving over [30], the two DNNs are trained separately and a third DNN combines them into an image with high fidelity at all bands. We demonstrate LS-DNN in two canonical inverse problems: super-resolution (SR) in diffraction-limited imaging (DLI), and quantitative phase retrieval (QPR). O"},"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":"1811.07945","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-19T19:29:20Z","cross_cats_sorted":[],"title_canon_sha256":"ee632f3147ec0999d4d03346d00a978a8376cedf57da76a2e19eda508c897a02","abstract_canon_sha256":"0b0ca0842c19ba51682544285dd8e5f4fb5cb7324431846df6b3ea95d156c7c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:17.281938Z","signature_b64":"iUahzUG6a//yPk7lOVWyHTmyvrnPgBg5Ay0dhpa+nlPXlwdnuuDJrfAQr1vLdYjaF2ym8rogjPI2PVwBXzhfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13fc5312fd8c6ed34cae31c2718540a6cdfc13a11c3512896d3b4393cca012dd","last_reissued_at":"2026-05-18T00:00:17.281299Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:17.281299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to synthesize: splitting and recombining low and high spatial frequencies for image recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"George Barbastathis, Mo Deng, Shuai Li","submitted_at":"2018-11-19T19:29:20Z","abstract_excerpt":"Deep Neural Network (DNN)-based image reconstruction, despite many successes, often exhibits uneven fidelity between high and low spatial frequency bands. In this paper we propose the Learning Synthesis by DNN (LS-DNN) approach where two DNNs process the low and high spatial frequencies, respectively, and, improving over [30], the two DNNs are trained separately and a third DNN combines them into an image with high fidelity at all bands. We demonstrate LS-DNN in two canonical inverse problems: super-resolution (SR) in diffraction-limited imaging (DLI), and quantitative phase retrieval (QPR). O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07945","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":""},"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":"1811.07945","created_at":"2026-05-18T00:00:17.281420+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.07945v1","created_at":"2026-05-18T00:00:17.281420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07945","created_at":"2026-05-18T00:00:17.281420+00:00"},{"alias_kind":"pith_short_12","alias_value":"CP6FGEX5RRXN","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CP6FGEX5RRXNGTFO","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CP6FGEX5","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.11713","citing_title":"Learning to Synthesize: Robust Phase Retrieval at Low Photon counts","ref_index":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CP6FGEX5RRXNGTFOGHBHDBKAU3","json":"https://pith.science/pith/CP6FGEX5RRXNGTFOGHBHDBKAU3.json","graph_json":"https://pith.science/api/pith-number/CP6FGEX5RRXNGTFOGHBHDBKAU3/graph.json","events_json":"https://pith.science/api/pith-number/CP6FGEX5RRXNGTFOGHBHDBKAU3/events.json","paper":"https://pith.science/paper/CP6FGEX5"},"agent_actions":{"view_html":"https://pith.science/pith/CP6FGEX5RRXNGTFOGHBHDBKAU3","download_json":"https://pith.science/pith/CP6FGEX5RRXNGTFOGHBHDBKAU3.json","view_paper":"https://pith.science/paper/CP6FGEX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.07945&json=true","fetch_graph":"https://pith.science/api/pith-number/CP6FGEX5RRXNGTFOGHBHDBKAU3/graph.json","fetch_events":"https://pith.science/api/pith-number/CP6FGEX5RRXNGTFOGHBHDBKAU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CP6FGEX5RRXNGTFOGHBHDBKAU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CP6FGEX5RRXNGTFOGHBHDBKAU3/action/storage_attestation","attest_author":"https://pith.science/pith/CP6FGEX5RRXNGTFOGHBHDBKAU3/action/author_attestation","sign_citation":"https://pith.science/pith/CP6FGEX5RRXNGTFOGHBHDBKAU3/action/citation_signature","submit_replication":"https://pith.science/pith/CP6FGEX5RRXNGTFOGHBHDBKAU3/action/replication_record"}},"created_at":"2026-05-18T00:00:17.281420+00:00","updated_at":"2026-05-18T00:00:17.281420+00:00"}