Dev

Electron Tomo — Dev Tier

(3 scenes)

Blind evaluation tier — no ground truth available.

What you get

Measurements (y), ideal forward operator (H), and spec ranges only.

How to use

Apply your pipeline from the Public tier. Use consistency as self-check.

What to submit

Reconstructed signals and corrected spec. Scored server-side.

Parameter Specifications

🔒

True spec hidden — estimate parameters from spec ranges below.

Parameter Spec Range Unit
tilt_angle -0.6 – 0.9 deg
tilt_axis -0.36 – 0.54 deg
defocus_gradient -12.0 – 18.0 nm/μm

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinET + gradient 0.754 30.95 0.93 0.86 ✓ Certified Wang et al., Ultramicroscopy 2023
2 DiffET + gradient 0.753 31.33 0.935 0.83 ✓ Certified Gao et al., NeurIPS 2024
3 TransET + gradient 0.715 28.69 0.895 0.85 ✓ Certified Li et al., Nat. Methods 2022
4 PhysET + gradient 0.685 26.79 0.853 0.88 ✓ Certified Chen et al., Nat. Commun. 2024
5 IsoNet + gradient 0.624 24.11 0.772 0.87 ✓ Certified Liu et al., Nat. Commun. 2021
6 DnCNN-ET + gradient 0.587 22.47 0.71 0.89 ✓ Certified Buchholz et al., Nat. Methods 2019
7 SIRT-ET + gradient 0.562 21.91 0.686 0.84 ✓ Certified Gilbert, J. Theor. Biol. 1972
8 WBP-ET + gradient 0.410 17.12 0.456 0.78 ✓ Certified Radermacher et al., J. Microsc. 1987
9 CS-ET + gradient 0.409 16.9 0.445 0.81 ✓ Certified Leary et al., Ultramicroscopy 2013

Visible Data Fields

y H_ideal spec_ranges

Dataset

Format: HDF5
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