Public
Entangled Photon Microscopy — Public Tier
(3 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 |
|---|---|---|---|
| pair_generation_rate | -2.0 – 4.0 | 1.0 | - |
| coincidence_window | -0.8 – 4.6 | 1.9 | ns |
| accidental_coincidence_rate | -4.0 – 8.0 | 2.0 | - |
| photon_loss_(per_arm) | -1.2 – 2.4 | 0.6 | dB |
InverseNet Baseline Scores
Method: CPU_baseline — Mismatch parameter: nominal
Scenario I (Ideal)
6.97 dB
SSIM 0.2037
Scenario II (Mismatch)
6.97 dB
SSIM 0.1457
Scenario III (Oracle)
10.09 dB
SSIM 0.2808
Per-scene breakdown (4 scenes)
| Scene | PSNR I | SSIM I | PSNR II | SSIM II | PSNR III | SSIM III |
|---|---|---|---|---|---|---|
| scene_00 | 6.67 | 0.1907 | 6.63 | 0.1348 | 9.76 | 0.2662 |
| scene_01 | 6.94 | 0.2009 | 6.94 | 0.1453 | 10.04 | 0.2786 |
| scene_02 | 7.55 | 0.2318 | 7.63 | 0.1622 | 10.73 | 0.3080 |
| scene_03 | 6.69 | 0.1916 | 6.70 | 0.1404 | 9.84 | 0.2704 |
Public Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | DiffGhost + gradient | 0.831 | 36.32 | 0.975 | 0.89 | ✓ Certified | Gao et al., NeurIPS 2024 |
| 2 | PhysGhost + gradient | 0.810 | 34.46 | 0.964 | 0.9 | ✓ Certified | Chen et al., Phys. Rev. Lett. 2024 |
| 3 | SwinGhost + gradient | 0.792 | 33.52 | 0.957 | 0.87 | ✓ Certified | Wang et al., npj Quantum Inf. 2023 |
| 4 | TransGhost + gradient | 0.765 | 31.32 | 0.935 | 0.89 | ✓ Certified | Li et al., Opt. Express 2022 |
| 5 | GAN-Ghost + gradient | 0.725 | 29.02 | 0.901 | 0.87 | ✓ Certified | Wang et al., Phys. Rev. A 2019 |
| 6 | DnCNN-Ghost + gradient | 0.670 | 26.06 | 0.834 | 0.88 | ✓ Certified | Lyu et al., Optica 2017 |
| 7 | SVD-Ghost + gradient | 0.583 | 22.11 | 0.695 | 0.92 | ✓ Certified | Gong et al., Sci. Rep. 2010 |
| 8 | CS-Ghost + gradient | 0.509 | 19.57 | 0.578 | 0.91 | ✓ Certified | Katz et al., Appl. Phys. Lett. 2009 |
| 9 | Coincidence-Count + gradient | 0.436 | 17.28 | 0.464 | 0.89 | ✓ Certified | Pittman et al., Phys. Rev. A 1995 |
Visible Data Fields
y
H_ideal
spec_ranges
x_true
true_spec
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%