{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DMCVCQBX4VQIII3NGECLRBEK23","short_pith_number":"pith:DMCVCQBX","schema_version":"1.0","canonical_sha256":"1b05514037e56084236d3104b8848ad6fb11bdc94705f13d362be40f11b8fbec","source":{"kind":"arxiv","id":"2012.12821","version":3},"attestation_state":"computed","paper":{"title":"Focal Frequency Loss for Image Reconstruction and Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bo Dai, Chen Change Loy, Liming Jiang, Wayne Wu","submitted_at":"2020-12-23T17:32:04Z","abstract_excerpt":"Image reconstruction and synthesis have witnessed remarkable progress thanks to the development of generative models. Nonetheless, gaps could still exist between the real and generated images, especially in the frequency domain. In this study, we show that narrowing gaps in the frequency domain can ameliorate image reconstruction and synthesis quality further. We propose a novel focal frequency loss, which allows a model to adaptively focus on frequency components that are hard to synthesize by down-weighting the easy ones. This objective function is complementary to existing spatial losses, 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":"2012.12821","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-23T17:32:04Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"0a7c3a131722bd614aef187b6b4f2004cc1236e8d240591a5aa8455d5630eb31","abstract_canon_sha256":"f95664986540d7627915876885923bd9616ece5e5392bbb88fa948286a03a10d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:45.959697Z","signature_b64":"LW2Uv3I1Q4c1SBvCDcZ+OAoTgLDhkUxIELSK/XFZUfRcLJf5pkHYeCxhEbWmiIOgvtPVyfytfCT0T44pNjKyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b05514037e56084236d3104b8848ad6fb11bdc94705f13d362be40f11b8fbec","last_reissued_at":"2026-07-05T03:07:45.959229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:45.959229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Focal Frequency Loss for Image Reconstruction and Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bo Dai, Chen Change Loy, Liming Jiang, Wayne Wu","submitted_at":"2020-12-23T17:32:04Z","abstract_excerpt":"Image reconstruction and synthesis have witnessed remarkable progress thanks to the development of generative models. Nonetheless, gaps could still exist between the real and generated images, especially in the frequency domain. In this study, we show that narrowing gaps in the frequency domain can ameliorate image reconstruction and synthesis quality further. We propose a novel focal frequency loss, which allows a model to adaptively focus on frequency components that are hard to synthesize by down-weighting the easy ones. This objective function is complementary to existing spatial losses, o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.12821","kind":"arxiv","version":3},"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/2012.12821/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":"2012.12821","created_at":"2026-07-05T03:07:45.959290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.12821v3","created_at":"2026-07-05T03:07:45.959290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.12821","created_at":"2026-07-05T03:07:45.959290+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMCVCQBX4VQI","created_at":"2026-07-05T03:07:45.959290+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMCVCQBX4VQIII3N","created_at":"2026-07-05T03:07:45.959290+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMCVCQBX","created_at":"2026-07-05T03:07:45.959290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10439","citing_title":"Removing Motion Artifact in MRI by Using a Perceptual Loss Driven Deep Learning Framework","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMCVCQBX4VQIII3NGECLRBEK23","json":"https://pith.science/pith/DMCVCQBX4VQIII3NGECLRBEK23.json","graph_json":"https://pith.science/api/pith-number/DMCVCQBX4VQIII3NGECLRBEK23/graph.json","events_json":"https://pith.science/api/pith-number/DMCVCQBX4VQIII3NGECLRBEK23/events.json","paper":"https://pith.science/paper/DMCVCQBX"},"agent_actions":{"view_html":"https://pith.science/pith/DMCVCQBX4VQIII3NGECLRBEK23","download_json":"https://pith.science/pith/DMCVCQBX4VQIII3NGECLRBEK23.json","view_paper":"https://pith.science/paper/DMCVCQBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.12821&json=true","fetch_graph":"https://pith.science/api/pith-number/DMCVCQBX4VQIII3NGECLRBEK23/graph.json","fetch_events":"https://pith.science/api/pith-number/DMCVCQBX4VQIII3NGECLRBEK23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMCVCQBX4VQIII3NGECLRBEK23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMCVCQBX4VQIII3NGECLRBEK23/action/storage_attestation","attest_author":"https://pith.science/pith/DMCVCQBX4VQIII3NGECLRBEK23/action/author_attestation","sign_citation":"https://pith.science/pith/DMCVCQBX4VQIII3NGECLRBEK23/action/citation_signature","submit_replication":"https://pith.science/pith/DMCVCQBX4VQIII3NGECLRBEK23/action/replication_record"}},"created_at":"2026-07-05T03:07:45.959290+00:00","updated_at":"2026-07-05T03:07:45.959290+00:00"}