Dev
SEM — Dev Tier
(3 scenes)Blind evaluation tier — no ground truth available.
What you get
Measurements (y), ideal forward operator (H), and spec ranges only.
How to use
Apply your pipeline from the Public tier. Use consistency as self-check.
What to submit
Reconstructed signals and corrected spec. Scored server-side.
Parameter Specifications
🔒
True spec hidden — estimate parameters from spec ranges below.
| Parameter | Spec Range | Unit |
|---|---|---|
| beam_energy | -0.12 – 0.18 | keV |
| stigmatism | -6.0 – 9.0 | nm |
| working_distance | -0.12 – 0.18 | mm |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | SwinIR + gradient | 0.716 | 29.08 | 0.902 | 0.82 | ✓ Certified | Liang et al., ICCVW 2021 |
| 2 | Wiener Filter + gradient | 0.569 | 22.26 | 0.701 | 0.83 | ✓ Certified | Analytical baseline |
| 3 | BM3D + gradient | 0.564 | 22.23 | 0.7 | 0.81 | ✓ Certified | Dabov et al., IEEE TIP 2007 |
| 4 | Noise2Void + gradient | 0.525 | 20.46 | 0.621 | 0.86 | ✓ Certified | Krull et al., CVPR 2019 |
Visible Data Fields
y
H_ideal
spec_ranges
Dataset
Format: HDF5
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%