Hidden

Ghost Imaging — Hidden Tier

(3 scenes)

Fully blind server-side evaluation — no data download.

No data downloadable. Algorithm runs server-side on hidden measurements.

Package algorithm as Docker container / Python script. Submit via link.

Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter	Spec Range	Unit
bucket_detector_efficiency	0.77 – 1.07	-
speckle_correlation_mismatch	-1.4 – 4.6	-
background_counts	-0.7 – 2.3	-
number_of_measurements	-2600.0 – 51400.0	-

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	Ghost-ViT + gradient	0.604	23.45	0.748	0.85	✓ Certified	Zhu et al., 2025
2	Quantum-ViT + gradient	0.584	22.61	0.715	0.86	✓ Certified	Quantum imaging transformer, 2024
3	CS-TVAL3 + gradient	0.505	20.13	0.605	0.81	✓ Certified	Li et al., 2014
4	Bayesian CS + gradient	0.504	20.07	0.602	0.81	✓ Certified	Bayesian compressed sensing
5	DRU-Net + gradient	0.491	19.98	0.598	0.76	✓ Certified	Wang et al., Sci. Rep. 2020
6	ScoreQuantum + gradient	0.488	19.76	0.587	0.78	✓ Certified	Wei et al., 2025
7	Photon Counting + gradient	0.460	19.07	0.553	0.74	✓ Certified	Classical baseline
8	Quantum-CNN + gradient	0.443	18.25	0.512	0.78	✓ Certified	Quantum imaging CNN
9	G(2)-Corr + gradient	0.387	15.73	0.388	0.87	✓ Certified	Pittman et al., PRA 1995
10	DiffusionQuantum + gradient	0.326	13.91	0.306	0.82	✓ Certified	Zhang et al., 2024

Scenes: 3

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

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