Public
Dark-Field Microscopy — Public Tier
(5 scenes)Full-access development tier with all data visible.
What you get
Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.
How to use
Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.
What to submit
Reconstructed signals (x_hat) and corrected spec as HDF5.
Parameter Specifications
✓
True spec visible — use these exact values for Scenario III oracle reconstruction.
| Parameter | Spec Range | True Value | Unit |
|---|---|---|---|
| condenser_na_vs_objective_na_ratio | 1.14 – 1.32 | 1.23 | - |
| stray_light | -1.0 – 2.0 | 0.5 | relative |
| scattering_angle_range | -0.15 – 0.15 | 0.0 | - |
InverseNet Baseline Scores
Method: CPU_baseline — Mismatch parameter: nominal
Scenario I (Ideal)
13.27 dB
SSIM 0.3991
Scenario II (Mismatch)
11.88 dB
SSIM 0.2385
Scenario III (Oracle)
19.75 dB
SSIM 0.4579
Per-scene breakdown (4 scenes)
| Scene | PSNR I | SSIM I | PSNR II | SSIM II | PSNR III | SSIM III |
|---|---|---|---|---|---|---|
| scene_00 | 17.02 | 0.3838 | 14.94 | 0.2440 | 20.04 | 0.5013 |
| scene_01 | 14.23 | 0.2969 | 12.92 | 0.2098 | 19.23 | 0.5480 |
| scene_02 | 8.52 | 0.3871 | 8.01 | 0.2308 | 20.11 | 0.3417 |
| scene_03 | 13.30 | 0.5284 | 11.66 | 0.2694 | 19.61 | 0.4408 |
Public Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | Restormer-DF + gradient | 0.853 | 37.48 | 0.98 | 0.93 | ✓ Certified | Zamir et al., CVPR 2022 (DF) |
| 2 | DiffusionDF + gradient | 0.850 | 38.31 | 0.983 | 0.87 | ✓ Certified | Luo et al., arXiv 2023 (DF) |
| 3 | SwinIR-DF + gradient | 0.840 | 36.58 | 0.976 | 0.92 | ✓ Certified | Liang et al., ICCV 2021 (DF) |
| 4 | Noise2Void-DF + gradient | 0.787 | 32.28 | 0.946 | 0.93 | ✓ Certified | Krull et al., CVPR 2019 (DF) |
| 5 | CARE-DF + gradient | 0.787 | 33.29 | 0.955 | 0.86 | ✓ Certified | Weigert et al., Nat. Methods 2018 (DF) |
| 6 | BM3D-DF + gradient | 0.768 | 30.87 | 0.929 | 0.94 | ✓ Certified | Dabov et al., IEEE TIP 2007 (DF adapt.) |
| 7 | TV-DF + gradient | 0.704 | 27.88 | 0.878 | 0.87 | ✓ Certified | Rudin et al., Physica D 1992 (DF) |
| 8 | Wiener-DF + gradient | 0.651 | 25.35 | 0.813 | 0.86 | ✓ Certified | Wiener, 1949 (DF adapt.) |
| 9 | Richardson-Lucy + gradient | 0.606 | 22.74 | 0.721 | 0.95 | ✓ Certified | Richardson, JOSA 1972; Lucy, AJ 1974 |
Visible Data Fields
y
H_ideal
spec_ranges
x_true
true_spec
Dataset
Format: HDF5
Scenes: 5
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%