Pith Number

pith:EHZB3QCK

pith:2026:EHZB3QCK4IGE3ZRIYOFND7CMDZ

not attested not anchored not stored refs resolved

Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs

Asad Ahmed, Dmitry Ignatov, Faraz Kayani, Radu Timofte, Sarmad Kayani

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.

arxiv:2605.03680 v1 · 2026-05-05 · cs.CV · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EHZB3QCK4IGE3ZRIYOFND7CMDZ}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest 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.

C2weakest 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.

C3one line summary

References

30 extracted · 30 resolved · 2 Pith anchors

[1] Abdelrahman Abdelhamed, Stephen Lin, and Michael S. Brown. A high-quality denoising dataset for smartphone cameras. InCVPR, pages 1692–1700, 2018. 2 2018

[2] Abdelrahman Abdelhamed, Radu Timofte, and Michael S. Brown. NTIRE 2019 challenge on real image denoising: Methods and results. InCVPRW, pages 0–0, 2019. 2 2019

[3] Abdelrahman Abdelhamed, Radu Timofte, and Michael S. Brown. NTIRE 2020 challenge on real image denoising: Dataset, methods and results. InCVPRW, pages 496–497, 2020

[4] Real image denoising with feature attention 2019

[5] Hinet: Half instance normalization network for image restoration 2021

Receipt and verification

First computed	2026-06-26T00:15:25.742466Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

21f21dc04ae20c4de628c38ad1fc4c1e4a70dd268889dcc74786ba971bdbaf4f

Aliases

arxiv: 2605.03680 · arxiv_version: 2605.03680v1 · doi: 10.48550/arxiv.2605.03680 · pith_short_12: EHZB3QCK4IGE · pith_short_16: EHZB3QCK4IGE3ZRI · pith_short_8: EHZB3QCK

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/EHZB3QCK4IGE3ZRIYOFND7CMDZ \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 21f21dc04ae20c4de628c38ad1fc4c1e4a70dd268889dcc74786ba971bdbaf4f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "682945cf8d4f1107465c0cee4ee65a2ef4f4499e4a34a7a445544088db922129",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-05T12:19:30Z",
    "title_canon_sha256": "14361b957f80377928a6e5dcdd8791b0ec0edb9f8447bffddd270b6042673fc2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.03680",
    "kind": "arxiv",
    "version": 1
  }
}