Hidden

Light-Sheet — Hidden Tier

(5 scenes)

Fully blind server-side evaluation — no data download.

What you get

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

How to use

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

What to submit

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

Parameter Specifications

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter Spec Range Unit
sheet_thickness -0.7 – 2.3 μm
sheet_tilt -0.35 – 1.15 deg
stripe_artifact -0.07 – 0.23

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 Restormer+ + gradient 0.746 31.11 0.932 0.81 ✓ Certified Zamir et al., ICCV 2024
2 ScoreMicro + gradient 0.733 30.4 0.923 0.8 ✓ Certified Wei et al., ECCV 2025
3 Restormer + gradient 0.733 30.38 0.922 0.8 ✓ Certified Zamir et al., CVPR 2022
4 DeconvFormer + gradient 0.710 29.7 0.912 0.74 ✓ Certified Chen et al., CVPR 2024
5 DiffDeconv + gradient 0.705 28.59 0.893 0.81 ✓ Certified Huang et al., NeurIPS 2024
6 PnP-DnCNN + gradient 0.670 26.62 0.849 0.82 ✓ Certified Zhang et al., IEEE TIP 2017
7 ResUNet + gradient 0.662 26.14 0.836 0.83 ✓ Certified DeCelle et al., Nat. Methods 2021
8 U-Net + gradient 0.656 26.43 0.844 0.77 ✓ Certified Ronneberger et al., MICCAI 2015
9 CARE + gradient 0.653 26.28 0.84 0.77 ✓ Certified Weigert et al., Nat. Methods 2018
10 TV-Deconvolution + gradient 0.649 26.12 0.835 0.77 ✓ Certified Rudin et al., Phys. A 1992
11 Wiener Filter + gradient 0.606 23.87 0.764 0.81 ✓ Certified Analytical baseline
12 Richardson-Lucy + gradient 0.572 22.13 0.696 0.86 ✓ Certified Richardson, JOSA 1972 / Lucy, AJ 1974
13 PnP-FISTA + gradient 0.564 22.44 0.708 0.78 ✓ Certified Bai et al., 2020

Dataset

Scenes: 5

Scoring Formula

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

PSNR: 40% SSIM: 40% Consistency: 20%
Back to Light-Sheet