Hidden

Electron Holography — 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
biprism_voltage -1.4 – 4.6 V
fringe_spacing -0.07 – 0.23 nm
partial_coherence -3.5 – 11.5 %

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinHolo + gradient 0.685 26.88 0.855 0.87 ✓ Certified Wang et al., Ultramicroscopy 2023
2 PhysHolo + gradient 0.667 26.11 0.835 0.86 ✓ Certified Chen et al., Nat. Commun. 2024
3 DiffHolo + gradient 0.659 26.79 0.853 0.75 ✓ Certified Gao et al., NeurIPS 2024
4 TransHolo + gradient 0.640 25.5 0.818 0.79 ✓ Certified Li et al., Nat. Commun. 2022
5 DeepHolo + gradient 0.606 23.46 0.749 0.86 ✓ Certified Rivenson et al., Optica 2018
6 DnCNN-Holo + gradient 0.571 22.5 0.711 0.81 ✓ Certified Gao et al., Ultramicroscopy 2019
7 WDD-Holo + gradient 0.475 18.78 0.539 0.86 ✓ Certified Lichte, Ultramicroscopy 1986
8 TV-Phase + gradient 0.420 17.73 0.487 0.74 ✓ Certified Beleggia et al., Ultramicroscopy 2004
9 FFT-Holo + gradient 0.403 16.31 0.416 0.87 ✓ Certified Lehmann & Lichte, Microsc. Microanal. 2002

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 Holography