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%