Dev

Ghost Imaging — Dev Tier

(3 scenes)

Blind evaluation tier — no ground truth available.

Measurements (y), ideal forward operator (H), and spec ranges only.

Apply your pipeline from the Public tier. Use consistency as self-check.

Reconstructed signals and corrected spec. Scored server-side.

🔒

True spec hidden — estimate parameters from spec ranges below.

Parameter	Spec Range	Unit
bucket_detector_efficiency	0.82 – 1.12	-
speckle_correlation_mismatch	-2.4 – 3.6	-
background_counts	-1.2 – 1.8	-
number_of_measurements	-11600.0 – 42400.0	-

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	Ghost-ViT + gradient	0.666	26.43	0.844	0.82	✓ Certified	Zhu et al., 2025
2	Quantum-ViT + gradient	0.648	25.39	0.814	0.84	✓ Certified	Quantum imaging transformer, 2024
3	ScoreQuantum + gradient	0.563	22.2	0.698	0.81	✓ Certified	Wei et al., 2025
4	Bayesian CS + gradient	0.546	21.5	0.668	0.82	✓ Certified	Bayesian compressed sensing
5	DRU-Net + gradient	0.542	21.05	0.648	0.86	✓ Certified	Wang et al., Sci. Rep. 2020
6	CS-TVAL3 + gradient	0.535	21.18	0.654	0.81	✓ Certified	Li et al., 2014
7	Photon Counting + gradient	0.522	20.64	0.629	0.82	✓ Certified	Classical baseline
8	Quantum-CNN + gradient	0.509	20.18	0.607	0.82	✓ Certified	Quantum imaging CNN
9	G(2)-Corr + gradient	0.448	18.13	0.506	0.82	✓ Certified	Pittman et al., PRA 1995
10	DiffusionQuantum + gradient	0.387	15.67	0.386	0.88	✓ Certified	Zhang et al., 2024

y H_ideal spec_ranges

Format: HDF5

Scenes: 3

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%