Hidden

Expansion Microscopy (ExM) — 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
expansion_factor 3.93 – 4.23 x
local_distortion -0.7 – 2.3 relative
anisotropic_expansion -0.42 – 1.38 xvsy

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffExM + gradient 0.741 29.86 0.915 0.88 ✓ Certified Gao et al., NeurIPS 2024
2 SwinExM + gradient 0.741 29.88 0.915 0.88 ✓ Certified Wang et al., Cell Syst. 2023
3 TransExM + gradient 0.728 29.95 0.916 0.81 ✓ Certified Li et al., Nat. Methods 2022
4 PhysExM + gradient 0.696 28.42 0.889 0.78 ✓ Certified Chen et al., Nat. Commun. 2024
5 DnCNN-ExM + gradient 0.606 23.45 0.748 0.86 ✓ Certified Zhao et al., Nat. Methods 2019
6 RL-ExM + gradient 0.577 23.09 0.735 0.76 ✓ Certified Richardson, J. Opt. Soc. Am. 1972
7 DeepInterp-ExM + gradient 0.531 21.46 0.666 0.75 ✓ Certified Lecoq et al., Nat. Methods 2021
8 Deconv-Exp + gradient 0.481 19.69 0.584 0.75 ✓ Certified Chen et al., Science 2015
9 TV-ExM + gradient 0.394 16.6 0.43 0.78 ✓ Certified Rudin et al., Physica D 1992

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 Expansion Microscopy (ExM)