Hidden

Image Scanning Microscopy (ISM) — 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.

Parameter	Spec Range	Unit
detector_element_offset	-0.14 – 0.46	px
magnification_error	-0.7 – 2.3	relative

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	Restormer+ + gradient	0.750	31.35	0.935	0.81	✓ Certified	Zamir et al., ICCV 2024
2	DeconvFormer + gradient	0.705	28.14	0.884	0.85	✓ Certified	Chen et al., CVPR 2024
3	ResUNet + gradient	0.680	27.35	0.866	0.8	✓ Certified	DeCelle et al., Nat. Methods 2021
4	ScoreMicro + gradient	0.665	27.08	0.86	0.75	✓ Certified	Wei et al., ECCV 2025
5	DiffDeconv + gradient	0.663	26.0	0.832	0.85	✓ Certified	Huang et al., NeurIPS 2024
6	TV-Deconvolution + gradient	0.654	25.57	0.82	0.85	✓ Certified	Rudin et al., Phys. A 1992
7	Restormer + gradient	0.651	25.55	0.819	0.84	✓ Certified	Zamir et al., CVPR 2022
8	CARE + gradient	0.640	24.8	0.796	0.87	✓ Certified	Weigert et al., Nat. Methods 2018
9	Wiener Filter + gradient	0.606	23.7	0.758	0.83	✓ Certified	Analytical baseline
10	Richardson-Lucy + gradient	0.594	23.46	0.749	0.8	✓ Certified	Richardson, JOSA 1972 / Lucy, AJ 1974
11	PnP-DnCNN + gradient	0.591	22.79	0.723	0.87	✓ Certified	Zhang et al., IEEE TIP 2017
12	PnP-FISTA + gradient	0.551	21.47	0.667	0.85	✓ Certified	Bai et al., 2020
13	U-Net + gradient	0.540	21.77	0.68	0.75	✓ Certified	Ronneberger et al., MICCAI 2015

Scenes: 5

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

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