{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QAA3IUJYDLYJOBSBGE6QIXBVVY","short_pith_number":"pith:QAA3IUJY","schema_version":"1.0","canonical_sha256":"8001b451381af0970641313d045c35ae03eff335063d21f4e9a8203632262e31","source":{"kind":"arxiv","id":"2503.20537","version":1},"attestation_state":"computed","paper":{"title":"TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiang Hu, Xiang Gao, Xiaoyun Zhang, Zhixin Wang, Ziying Zhang","submitted_at":"2025-03-26T13:35:43Z","abstract_excerpt":"Diffusion-based methodologies have shown significant potential in blind face restoration (BFR), leveraging their robust generative capabilities. However, they are often criticized for two significant problems: 1) slow training and inference speed, and 2) inadequate recovery of fine-grained facial details. To address these problems, we propose a novel Truncated Diffusion model for efficient Blind Face Restoration (TD-BFR), a three-stage paradigm tailored for the progressive resolution of degraded images. Specifically, TD-BFR utilizes an innovative truncated sampling method, starting from low-qu"},"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":"2503.20537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T13:35:43Z","cross_cats_sorted":[],"title_canon_sha256":"2d156d14a4f0abc0c85a0fb0b0608c54a68e9a1da50ccb56ab3a566f15d14a22","abstract_canon_sha256":"d94e75a35e0b0935308a17140102bb768250d45452349a7223f67f6452612c40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:39.819689Z","signature_b64":"lJplkjPyiRLJNspnpT4zSa202SVRSUELLgqk2Teef8pETh9ZrYYxqFLvzlhiG7Fadr3LlPQYqCX2AYB9OZeyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8001b451381af0970641313d045c35ae03eff335063d21f4e9a8203632262e31","last_reissued_at":"2026-07-05T10:39:39.819214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:39.819214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiang Hu, Xiang Gao, Xiaoyun Zhang, Zhixin Wang, Ziying Zhang","submitted_at":"2025-03-26T13:35:43Z","abstract_excerpt":"Diffusion-based methodologies have shown significant potential in blind face restoration (BFR), leveraging their robust generative capabilities. However, they are often criticized for two significant problems: 1) slow training and inference speed, and 2) inadequate recovery of fine-grained facial details. To address these problems, we propose a novel Truncated Diffusion model for efficient Blind Face Restoration (TD-BFR), a three-stage paradigm tailored for the progressive resolution of degraded images. Specifically, TD-BFR utilizes an innovative truncated sampling method, starting from low-qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20537","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/2503.20537/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":"2503.20537","created_at":"2026-07-05T10:39:39.819290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20537v1","created_at":"2026-07-05T10:39:39.819290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20537","created_at":"2026-07-05T10:39:39.819290+00:00"},{"alias_kind":"pith_short_12","alias_value":"QAA3IUJYDLYJ","created_at":"2026-07-05T10:39:39.819290+00:00"},{"alias_kind":"pith_short_16","alias_value":"QAA3IUJYDLYJOBSB","created_at":"2026-07-05T10:39:39.819290+00:00"},{"alias_kind":"pith_short_8","alias_value":"QAA3IUJY","created_at":"2026-07-05T10:39:39.819290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17910","citing_title":"DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QAA3IUJYDLYJOBSBGE6QIXBVVY","json":"https://pith.science/pith/QAA3IUJYDLYJOBSBGE6QIXBVVY.json","graph_json":"https://pith.science/api/pith-number/QAA3IUJYDLYJOBSBGE6QIXBVVY/graph.json","events_json":"https://pith.science/api/pith-number/QAA3IUJYDLYJOBSBGE6QIXBVVY/events.json","paper":"https://pith.science/paper/QAA3IUJY"},"agent_actions":{"view_html":"https://pith.science/pith/QAA3IUJYDLYJOBSBGE6QIXBVVY","download_json":"https://pith.science/pith/QAA3IUJYDLYJOBSBGE6QIXBVVY.json","view_paper":"https://pith.science/paper/QAA3IUJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20537&json=true","fetch_graph":"https://pith.science/api/pith-number/QAA3IUJYDLYJOBSBGE6QIXBVVY/graph.json","fetch_events":"https://pith.science/api/pith-number/QAA3IUJYDLYJOBSBGE6QIXBVVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QAA3IUJYDLYJOBSBGE6QIXBVVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QAA3IUJYDLYJOBSBGE6QIXBVVY/action/storage_attestation","attest_author":"https://pith.science/pith/QAA3IUJYDLYJOBSBGE6QIXBVVY/action/author_attestation","sign_citation":"https://pith.science/pith/QAA3IUJYDLYJOBSBGE6QIXBVVY/action/citation_signature","submit_replication":"https://pith.science/pith/QAA3IUJYDLYJOBSBGE6QIXBVVY/action/replication_record"}},"created_at":"2026-07-05T10:39:39.819290+00:00","updated_at":"2026-07-05T10:39:39.819290+00:00"}