{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EHZB3QCK4IGE3ZRIYOFND7CMDZ","short_pith_number":"pith:EHZB3QCK","schema_version":"1.0","canonical_sha256":"21f21dc04ae20c4de628c38ad1fc4c1e4a70dd268889dcc74786ba971bdbaf4f","source":{"kind":"arxiv","id":"2605.03680","version":1},"attestation_state":"computed","paper":{"title":"Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A 1.96M-parameter LiteDenoiseNet student model achieves 37.58 dB PSNR on full-resolution real image denoising benchmarks while running in 34-46 ms on mobile NPUs by leveraging NPU-compatible primitives and high-alpha knowledge distillation.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Asad Ahmed, Dmitry Ignatov, Faraz Kayani, Radu Timofte, Sarmad Kayani","submitted_at":"2026-05-05T12:19:30Z","abstract_excerpt":"While deep-learning-based image restoration has achieved unprecedented fidelity, deployment on mobile Neural Processing Units (NPUs) remains bottlenecked by operator incompatibility and memory-access overhead. We propose an NPU-aware hardware-algorithm co-design approach for real-world image denoising on mobile NPUs. Our approach employs a high-capacity teacher to supervise a lightweight student network specifically designed to leverage the tiled-memory architectures of modern mobile SoCs. By prioritizing NPU-native primitives -- standard 3x3 convolutions, ReLU activations, and nearest-neighbo"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.03680","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-05T12:19:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"14361b957f80377928a6e5dcdd8791b0ec0edb9f8447bffddd270b6042673fc2","abstract_canon_sha256":"682945cf8d4f1107465c0cee4ee65a2ef4f4499e4a34a7a445544088db922129"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:25.742943Z","signature_b64":"PtJsYI+sgaaTpdVti6VOxqCaCzNx34l6XUCn3HZY0gLwlQJCaSrGfA58aQTQB5oIEDYSoWUUXtW2T4dC0bEACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21f21dc04ae20c4de628c38ad1fc4c1e4a70dd268889dcc74786ba971bdbaf4f","last_reissued_at":"2026-06-26T00:15:25.742466Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:25.742466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A 1.96M-parameter LiteDenoiseNet student model achieves 37.58 dB PSNR on full-resolution real image denoising benchmarks while running in 34-46 ms on mobile NPUs by leveraging NPU-compatible primitives and high-alpha knowledge distillation.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Asad Ahmed, Dmitry Ignatov, Faraz Kayani, Radu Timofte, Sarmad Kayani","submitted_at":"2026-05-05T12:19:30Z","abstract_excerpt":"While deep-learning-based image restoration has achieved unprecedented fidelity, deployment on mobile Neural Processing Units (NPUs) remains bottlenecked by operator incompatibility and memory-access overhead. We propose an NPU-aware hardware-algorithm co-design approach for real-world image denoising on mobile NPUs. Our approach employs a high-capacity teacher to supervise a lightweight student network specifically designed to leverage the tiled-memory architectures of modern mobile SoCs. By prioritizing NPU-native primitives -- standard 3x3 convolutions, ReLU activations, and nearest-neighbo"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"The 1.96M-parameter student recovers 99.8% of the teacher's restoration quality via high-alpha knowledge distillation (alpha = 0.9), achieving a 21.2x parameter reduction while closing the PSNR gap from 1.63 dB to only 0.05 dB.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That restricting the student to NPU-native primitives (3x3 convolutions, ReLU, nearest-neighbor upsampling) combined with progressive context expansion up to 1024x1024 crops will preserve generalization on real-world noisy images without significant quality loss outside the specific Mobile AI 2026 benchmarks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A 1.96M-parameter LiteDenoiseNet student model achieves 37.58 dB PSNR on full-resolution real image denoising benchmarks while running in 34-46 ms on mobile NPUs by leveraging NPU-compatible primitives and high-alpha knowledge distillation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"f36e721f99bb769c0246475716a945e5ef32fc83a607ec832d3da8448df10d3b"},"source":{"id":"2605.03680","kind":"arxiv","version":1},"verdict":{"id":"986ad60d-41d1-4416-8a0a-62f5ebf607a9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T17:55:39.329059Z","strongest_claim":"The 1.96M-parameter student recovers 99.8% of the teacher's restoration quality via high-alpha knowledge distillation (alpha = 0.9), achieving a 21.2x parameter reduction while closing the PSNR gap from 1.63 dB to only 0.05 dB.","one_line_summary":"A 1.96M-parameter LiteDenoiseNet student model achieves 37.58 dB PSNR on full-resolution real image denoising benchmarks while running in 34-46 ms on mobile NPUs by leveraging NPU-compatible primitives and high-alpha knowledge distillation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That restricting the student to NPU-native primitives (3x3 convolutions, ReLU, nearest-neighbor upsampling) combined with progressive context expansion up to 1024x1024 crops will preserve generalization on real-world noisy images without significant quality loss outside the specific Mobile AI 2026 benchmarks.","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.03680/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T13:36:25.249369Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T00:31:21.545513Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:06:14.581799Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"942c313fa52c2682407f1e9bb4b983f04ed10f0bc90f074dd604a4e60c26fbb0"},"references":{"count":30,"sample":[{"doi":"","year":2018,"title":"Abdelrahman Abdelhamed, Stephen Lin, and Michael S. Brown. A high-quality denoising dataset for smartphone cameras. InCVPR, pages 1692–1700, 2018. 2","work_id":"4b8cf503-8324-4766-98e7-9286ae010ac7","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Abdelrahman Abdelhamed, Radu Timofte, and Michael S. Brown. NTIRE 2019 challenge on real image denoising: Methods and results. InCVPRW, pages 0–0, 2019. 2","work_id":"bb8e0d6a-6bcb-4011-8c92-9e88bed61f0d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Abdelrahman Abdelhamed, Radu Timofte, and Michael S. Brown. NTIRE 2020 challenge on real image denoising: Dataset, methods and results. InCVPRW, pages 496–497,","work_id":"677e60f8-8340-493b-b3ba-da8a234fff49","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Real image denoising with feature attention","work_id":"a438b169-e5e8-41d8-8571-b778c71c47c7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Hinet: Half instance normalization network for image restoration","work_id":"b0e6b4c1-eb9b-4179-be1d-20b04f665bbc","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":30,"snapshot_sha256":"066c1d1e7c61f6c2d4706ed64f9f34412797e21a56352a39d42c53207cd078d6","internal_anchors":2},"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":"2605.03680","created_at":"2026-06-26T00:15:25.742521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.03680v1","created_at":"2026-06-26T00:15:25.742521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03680","created_at":"2026-06-26T00:15:25.742521+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHZB3QCK4IGE","created_at":"2026-06-26T00:15:25.742521+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHZB3QCK4IGE3ZRI","created_at":"2026-06-26T00:15:25.742521+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHZB3QCK","created_at":"2026-06-26T00:15:25.742521+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/EHZB3QCK4IGE3ZRIYOFND7CMDZ","json":"https://pith.science/pith/EHZB3QCK4IGE3ZRIYOFND7CMDZ.json","graph_json":"https://pith.science/api/pith-number/EHZB3QCK4IGE3ZRIYOFND7CMDZ/graph.json","events_json":"https://pith.science/api/pith-number/EHZB3QCK4IGE3ZRIYOFND7CMDZ/events.json","paper":"https://pith.science/paper/EHZB3QCK"},"agent_actions":{"view_html":"https://pith.science/pith/EHZB3QCK4IGE3ZRIYOFND7CMDZ","download_json":"https://pith.science/pith/EHZB3QCK4IGE3ZRIYOFND7CMDZ.json","view_paper":"https://pith.science/paper/EHZB3QCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.03680&json=true","fetch_graph":"https://pith.science/api/pith-number/EHZB3QCK4IGE3ZRIYOFND7CMDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/EHZB3QCK4IGE3ZRIYOFND7CMDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHZB3QCK4IGE3ZRIYOFND7CMDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHZB3QCK4IGE3ZRIYOFND7CMDZ/action/storage_attestation","attest_author":"https://pith.science/pith/EHZB3QCK4IGE3ZRIYOFND7CMDZ/action/author_attestation","sign_citation":"https://pith.science/pith/EHZB3QCK4IGE3ZRIYOFND7CMDZ/action/citation_signature","submit_replication":"https://pith.science/pith/EHZB3QCK4IGE3ZRIYOFND7CMDZ/action/replication_record"}},"created_at":"2026-06-26T00:15:25.742521+00:00","updated_at":"2026-06-26T00:15:25.742521+00:00"}