Hidden

Electron Tomo — Hidden Tier

(3 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
tilt_angle -0.35 – 1.15 deg
tilt_axis -0.21 – 0.69 deg
defocus_gradient -7.0 – 23.0 nm/μm

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinET + gradient 0.732 29.47 0.908 0.87 ✓ Certified Wang et al., Ultramicroscopy 2023
2 DiffET + gradient 0.706 29.0 0.9 0.78 ✓ Certified Gao et al., NeurIPS 2024
3 PhysET + gradient 0.619 24.74 0.794 0.77 ✓ Certified Chen et al., Nat. Commun. 2024
4 TransET + gradient 0.594 23.08 0.734 0.85 ✓ Certified Li et al., Nat. Methods 2022
5 IsoNet + gradient 0.588 23.53 0.751 0.76 ✓ Certified Liu et al., Nat. Commun. 2021
6 DnCNN-ET + gradient 0.552 21.34 0.661 0.87 ✓ Certified Buchholz et al., Nat. Methods 2019
7 SIRT-ET + gradient 0.508 20.56 0.625 0.76 ✓ Certified Gilbert, J. Theor. Biol. 1972
8 WBP-ET + gradient 0.382 16.17 0.41 0.78 ✓ Certified Radermacher et al., J. Microsc. 1987
9 CS-ET + gradient 0.338 14.0 0.31 0.87 ✓ Certified Leary et al., Ultramicroscopy 2013

Dataset

Scenes: 3

Scoring Formula

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

PSNR: 40% SSIM: 40% Consistency: 20%
Back to Electron Tomo