Hidden
Magnetic Force Microscopy (MFM) — 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 |
|---|---|---|
| lift_height | 29.0 – 119.0 | nm |
| tip_magnetization_model | -0.15 – 0.15 | - |
| electrostatic_coupling | -1.4 – 4.6 | - |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | SPM-Former + gradient | 0.617 | 23.81 | 0.762 | 0.87 | ✓ Certified | Chen et al., NanoLett 2024 |
| 2 | U-Net-SPM + gradient | 0.581 | 22.8 | 0.723 | 0.82 | ✓ Certified | SPM U-Net variant |
| 3 | E2E-BTR + gradient | 0.522 | 20.31 | 0.613 | 0.87 | ✓ Certified | Kossler et al., Sci. Rep. 2022 |
| 4 | MLE Reconstruction + gradient | 0.519 | 20.9 | 0.641 | 0.77 | ✓ Certified | Classical statistical method |
| 5 | DeepSPM + gradient | 0.503 | 19.64 | 0.581 | 0.87 | ✓ Certified | Alldritt et al., Commun. Phys. 2020 |
| 6 | BTR + gradient | 0.494 | 20.23 | 0.61 | 0.74 | ✓ Certified | Villarrubia, JRNIST 1997 |
| 7 | DiffusionSPM + gradient | 0.473 | 18.7 | 0.535 | 0.86 | ✓ Certified | Zhang et al., 2024 |
| 8 | TV-Deconvolution + gradient | 0.464 | 18.86 | 0.543 | 0.79 | ✓ Certified | TV regularization for SPM |
| 9 | ScoreSPM + gradient | 0.448 | 18.35 | 0.517 | 0.79 | ✓ Certified | Wei et al., 2025 |
| 10 | Reg-Deconv + gradient | 0.426 | 17.19 | 0.46 | 0.85 | ✓ Certified | Dongmo et al., 2000 |
Dataset
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%