Public

Ghost Imaging — 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
bucket_detector_efficiency 0.8 – 1.1 0.95 -
speckle_correlation_mismatch -2.0 – 4.0 1.0 -
background_counts -1.0 – 2.0 0.5 -
number_of_measurements -8000.0 – 46000.0 19000.0 -

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

8.23 dB

SSIM 0.0225

Scenario II (Mismatch)

8.22 dB

SSIM 0.0224

Scenario III (Oracle)

8.12 dB

SSIM 0.0204

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 5.83 0.0079 5.79 0.0078 5.94 0.0051
scene_01 6.13 0.0023 6.14 0.0024 5.98 0.0025
scene_02 5.80 0.0183 5.80 0.0183 5.79 0.0200
scene_03 15.18 0.0613 15.17 0.0612 14.79 0.0539

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 ScoreQuantum + gradient 0.725 28.48 0.891 0.92 ✓ Certified Wei et al., 2025
2 Ghost-ViT + gradient 0.705 27.8 0.877 0.88 ✓ Certified Zhu et al., 2025
3 Quantum-ViT + gradient 0.685 26.86 0.855 0.87 ✓ Certified Quantum imaging transformer, 2024
4 DRU-Net + gradient 0.678 26.63 0.849 0.86 ✓ Certified Wang et al., Sci. Rep. 2020
5 Quantum-CNN + gradient 0.676 26.32 0.841 0.88 ✓ Certified Quantum imaging CNN
6 DiffusionQuantum + gradient 0.628 24.12 0.773 0.89 ✓ Certified Zhang et al., 2024
7 Bayesian CS + gradient 0.600 23.16 0.737 0.87 ✓ Certified Bayesian compressed sensing
8 CS-TVAL3 + gradient 0.581 22.17 0.697 0.9 ✓ Certified Li et al., 2014
9 Photon Counting + gradient 0.560 21.12 0.651 0.94 ✓ Certified Classical baseline
10 G(2)-Corr + gradient 0.483 18.9 0.545 0.88 ✓ Certified Pittman et al., PRA 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%
Back to Ghost Imaging