{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VD6YFWFQZGDEUKSJA7F6JFMM46","short_pith_number":"pith:VD6YFWFQ","schema_version":"1.0","canonical_sha256":"a8fd82d8b0c9864a2a4907cbe4958ce7bbdfb1731985938351d023fdbd5d7cac","source":{"kind":"arxiv","id":"2405.20392","version":1},"attestation_state":"computed","paper":{"title":"Can No-Reference Quality-Assessment Methods Serve as Perceptual Losses for Super-Resolution?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Dmitriy Vatolin, Egor Chistov, Egor Kashkarov, Ivan Molodetskikh","submitted_at":"2024-05-30T18:04:58Z","abstract_excerpt":"Perceptual losses play an important role in constructing deep-neural-network-based methods by increasing the naturalness and realism of processed images and videos. Use of perceptual losses is often limited to LPIPS, a fullreference method. Even though deep no-reference image-qualityassessment methods are excellent at predicting human judgment, little research has examined their incorporation in loss functions. This paper investigates direct optimization of several video-superresolution models using no-reference image-quality-assessment methods as perceptual losses. Our experimental results sh"},"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":"2405.20392","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2024-05-30T18:04:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"445e201d1bc570d4ed7ad4ff9234a58b4808e106ac4d4f64778f6fa233d67cb7","abstract_canon_sha256":"62791487385f431c7580b5ded5f34a9c8c3406f95f7895cd915cc2e892f61df9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:36.890017Z","signature_b64":"zBvRrPWGDQTfQe3eS6+B1zET2qbYELLNmKl5za0x1k6SMjkDbeVBjl1VGA5RypC2ks//sZGqIPyp8UEwutd3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8fd82d8b0c9864a2a4907cbe4958ce7bbdfb1731985938351d023fdbd5d7cac","last_reissued_at":"2026-07-05T08:25:36.889601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:36.889601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can No-Reference Quality-Assessment Methods Serve as Perceptual Losses for Super-Resolution?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Dmitriy Vatolin, Egor Chistov, Egor Kashkarov, Ivan Molodetskikh","submitted_at":"2024-05-30T18:04:58Z","abstract_excerpt":"Perceptual losses play an important role in constructing deep-neural-network-based methods by increasing the naturalness and realism of processed images and videos. Use of perceptual losses is often limited to LPIPS, a fullreference method. Even though deep no-reference image-qualityassessment methods are excellent at predicting human judgment, little research has examined their incorporation in loss functions. This paper investigates direct optimization of several video-superresolution models using no-reference image-quality-assessment methods as perceptual losses. Our experimental results sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20392","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/2405.20392/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":"2405.20392","created_at":"2026-07-05T08:25:36.889656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20392v1","created_at":"2026-07-05T08:25:36.889656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20392","created_at":"2026-07-05T08:25:36.889656+00:00"},{"alias_kind":"pith_short_12","alias_value":"VD6YFWFQZGDE","created_at":"2026-07-05T08:25:36.889656+00:00"},{"alias_kind":"pith_short_16","alias_value":"VD6YFWFQZGDEUKSJ","created_at":"2026-07-05T08:25:36.889656+00:00"},{"alias_kind":"pith_short_8","alias_value":"VD6YFWFQ","created_at":"2026-07-05T08:25:36.889656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12575","citing_title":"Stochastic BIQA: Median Randomized Smoothing for Certified Blind Image Quality Assessment","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VD6YFWFQZGDEUKSJA7F6JFMM46","json":"https://pith.science/pith/VD6YFWFQZGDEUKSJA7F6JFMM46.json","graph_json":"https://pith.science/api/pith-number/VD6YFWFQZGDEUKSJA7F6JFMM46/graph.json","events_json":"https://pith.science/api/pith-number/VD6YFWFQZGDEUKSJA7F6JFMM46/events.json","paper":"https://pith.science/paper/VD6YFWFQ"},"agent_actions":{"view_html":"https://pith.science/pith/VD6YFWFQZGDEUKSJA7F6JFMM46","download_json":"https://pith.science/pith/VD6YFWFQZGDEUKSJA7F6JFMM46.json","view_paper":"https://pith.science/paper/VD6YFWFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20392&json=true","fetch_graph":"https://pith.science/api/pith-number/VD6YFWFQZGDEUKSJA7F6JFMM46/graph.json","fetch_events":"https://pith.science/api/pith-number/VD6YFWFQZGDEUKSJA7F6JFMM46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VD6YFWFQZGDEUKSJA7F6JFMM46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VD6YFWFQZGDEUKSJA7F6JFMM46/action/storage_attestation","attest_author":"https://pith.science/pith/VD6YFWFQZGDEUKSJA7F6JFMM46/action/author_attestation","sign_citation":"https://pith.science/pith/VD6YFWFQZGDEUKSJA7F6JFMM46/action/citation_signature","submit_replication":"https://pith.science/pith/VD6YFWFQZGDEUKSJA7F6JFMM46/action/replication_record"}},"created_at":"2026-07-05T08:25:36.889656+00:00","updated_at":"2026-07-05T08:25:36.889656+00:00"}