Hidden

Focused Ion Beam SEM (FIB-SEM) — 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
slice_thickness_variation -2.1 – 6.9 -
curtaining_artifact -0.042 – 0.138 relative
charging -42.0 – 138.0 V
drift_between_slices -0.7 – 2.3 nm

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PhysFIB + gradient 0.746 31.26 0.934 0.8 ✓ Certified Chen et al., Nat. Commun. 2024
2 DiffFIB + gradient 0.731 30.9 0.93 0.75 ✓ Certified Gao et al., NeurIPS 2024
3 SwinFIB + gradient 0.703 29.06 0.901 0.76 ✓ Certified Wang et al., Nat. Commun. 2023
4 TransFIB + gradient 0.679 27.7 0.874 0.76 ✓ Certified Li et al., Nat. Methods 2022
5 BM3D-FIB + gradient 0.603 23.65 0.756 0.82 ✓ Certified Dabov et al., IEEE TIP 2007
6 DnCNN-FIB + gradient 0.579 22.63 0.716 0.83 ✓ Certified Buchholz et al., Nat. Methods 2019
7 NLM-FIB + gradient 0.551 21.97 0.689 0.78 ✓ Certified Buades et al., CVPR 2005
8 TV-FIB + gradient 0.533 20.95 0.643 0.83 ✓ Certified Rudin et al., Physica D 1992
9 N2V-FIB + gradient 0.489 19.44 0.572 0.83 ✓ Certified Krull et al., NeurIPS 2019

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 Focused Ion Beam SEM (FIB-SEM)