Hidden

Near-field Scanning Optical Microscopy (NSOM) — Hidden Tier

(3 scenes)

Fully blind server-side evaluation — no data download.

What you get

No data downloadable. Algorithm runs server-side on hidden measurements.

How to use

Package algorithm as Docker container / Python script. Submit via link.

What to submit

Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

Parameter Specifications

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter Spec Range Unit
tip_sample_distance 4.4 – 28.4 nm
aperture_size_error -2.8 – 9.2 -
topographic_coupling -4.2 – 13.8 -
far_field_background -2.8 – 9.2 -

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 U-Net-SPM + gradient 0.596 23.21 0.739 0.84 ✓ Certified SPM U-Net variant
2 DiffusionSPM + gradient 0.592 23.08 0.734 0.84 ✓ Certified Zhang et al., 2024
3 E2E-BTR + gradient 0.567 22.49 0.711 0.79 ✓ Certified Kossler et al., Sci. Rep. 2022
4 SPM-Former + gradient 0.557 21.58 0.672 0.86 ✓ Certified Chen et al., NanoLett 2024
5 ScoreSPM + gradient 0.547 21.89 0.685 0.77 ✓ Certified Wei et al., 2025
6 Reg-Deconv + gradient 0.535 21.58 0.672 0.75 ✓ Certified Dongmo et al., 2000
7 MLE Reconstruction + gradient 0.508 20.56 0.625 0.76 ✓ Certified Classical statistical method
8 BTR + gradient 0.504 20.43 0.619 0.76 ✓ Certified Villarrubia, JRNIST 1997
9 DeepSPM + gradient 0.414 17.39 0.47 0.76 ✓ Certified Alldritt et al., Commun. Phys. 2020
10 TV-Deconvolution + gradient 0.395 16.22 0.412 0.84 ✓ Certified TV regularization for SPM

Dataset

Scenes: 3

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to Near-field Scanning Optical Microscopy (NSOM)