Hidden

Two-Photon — Hidden Tier

(5 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.

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	DeconvFormer + gradient	0.760	31.27	0.934	0.87	✓ Certified	Chen et al., CVPR 2024
2	Restormer+ + gradient	0.720	29.55	0.91	0.8	✓ Certified	Zamir et al., ICCV 2024
3	Restormer + gradient	0.710	29.09	0.902	0.79	✓ Certified	Zamir et al., CVPR 2022
4	U-Net + gradient	0.686	27.02	0.859	0.86	✓ Certified	Ronneberger et al., MICCAI 2015
5	DiffDeconv + gradient	0.675	26.67	0.85	0.84	✓ Certified	Huang et al., NeurIPS 2024
6	ScoreMicro + gradient	0.673	26.99	0.858	0.8	✓ Certified	Wei et al., ECCV 2025
7	CARE + gradient	0.628	24.26	0.778	0.87	✓ Certified	Weigert et al., Nat. Methods 2018
8	TV-Deconvolution + gradient	0.620	25.05	0.804	0.74	✓ Certified	Rudin et al., Phys. A 1992
9	Richardson-Lucy + gradient	0.606	24.36	0.781	0.75	✓ Certified	Richardson, JOSA 1972 / Lucy, AJ 1974
10	Wiener Filter + gradient	0.604	23.52	0.751	0.84	✓ Certified	Analytical baseline
11	PnP-DnCNN + gradient	0.600	23.52	0.751	0.82	✓ Certified	Zhang et al., IEEE TIP 2017
12	ResUNet + gradient	0.583	23.42	0.747	0.75	✓ Certified	DeCelle et al., Nat. Methods 2021
13	PnP-FISTA + gradient	0.519	20.34	0.615	0.85	✓ Certified	Bai et al., 2020

Scenes: 5

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

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