Dev

Electron Holography — 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
biprism_voltage -2.4 – 3.6 V
fringe_spacing -0.12 – 0.18 nm
partial_coherence -6.0 – 9.0 %

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinHolo + gradient 0.742 30.87 0.929 0.81 ✓ Certified Wang et al., Ultramicroscopy 2023
2 DiffHolo + gradient 0.730 30.21 0.92 0.8 ✓ Certified Gao et al., NeurIPS 2024
3 TransHolo + gradient 0.718 29.09 0.902 0.83 ✓ Certified Li et al., Nat. Commun. 2022
4 PhysHolo + gradient 0.704 28.67 0.894 0.8 ✓ Certified Chen et al., Nat. Commun. 2024
5 DeepHolo + gradient 0.661 25.56 0.819 0.89 ✓ Certified Rivenson et al., Optica 2018
6 DnCNN-Holo + gradient 0.603 23.58 0.753 0.83 ✓ Certified Gao et al., Ultramicroscopy 2019
7 WDD-Holo + gradient 0.504 19.75 0.587 0.86 ✓ Certified Lichte, Ultramicroscopy 1986
8 TV-Phase + gradient 0.501 19.97 0.597 0.81 ✓ Certified Beleggia et al., Ultramicroscopy 2004
9 FFT-Holo + gradient 0.440 17.54 0.477 0.87 ✓ Certified Lehmann & Lichte, Microsc. Microanal. 2002

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 Holography