Dev

Spinning Disk Confocal Microscopy — Dev Tier

(5 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
pinhole_crosstalk	-3.6 – 5.4	-
disk_rotation_wobble	-0.24 – 0.36	px
illumination_non_uniformity	-2.4 – 3.6	-

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	Restormer+ + gradient	0.778	32.51	0.948	0.87	✓ Certified	Zamir et al., ICCV 2024
2	DeconvFormer + gradient	0.773	31.88	0.941	0.89	✓ Certified	Chen et al., CVPR 2024
3	Restormer + gradient	0.727	28.91	0.899	0.89	✓ Certified	Zamir et al., CVPR 2022
4	ScoreMicro + gradient	0.725	29.17	0.903	0.86	✓ Certified	Wei et al., ECCV 2025
5	ResUNet + gradient	0.722	29.33	0.906	0.83	✓ Certified	DeCelle et al., Nat. Methods 2021
6	U-Net + gradient	0.672	26.26	0.839	0.87	✓ Certified	Ronneberger et al., MICCAI 2015
7	DiffDeconv + gradient	0.670	26.33	0.841	0.85	✓ Certified	Huang et al., NeurIPS 2024
8	CARE + gradient	0.664	25.6	0.821	0.9	✓ Certified	Weigert et al., Nat. Methods 2018
9	PnP-FISTA + gradient	0.649	25.54	0.819	0.83	✓ Certified	Bai et al., 2020
10	PnP-DnCNN + gradient	0.648	25.68	0.823	0.81	✓ Certified	Zhang et al., IEEE TIP 2017
11	TV-Deconvolution + gradient	0.643	24.93	0.8	0.87	✓ Certified	Rudin et al., Phys. A 1992
12	Wiener Filter + gradient	0.638	24.63	0.79	0.88	✓ Certified	Analytical baseline
13	Richardson-Lucy + gradient	0.623	24.42	0.783	0.83	✓ Certified	Richardson, JOSA 1972 / Lucy, AJ 1974

y H_ideal spec_ranges

Format: HDF5

Scenes: 5

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

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