Hidden

X-ray Fluorescence Tomography — Hidden Tier

(5 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
self_absorption_correction -4.2 – 13.8 -
rotation_axis_offset -0.42 – 1.38 px
fluorescence_yield_error -1.4 – 4.6 -
dead_time_at_high_count_rate -1.4 – 4.6 -

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 CalibFormer + gradient 0.643 25.81 0.827 0.77 ✓ Certified Transformer calibration, 2024
2 Calibration-Lookup + gradient 0.628 24.78 0.795 0.81 ✓ Certified Look-up table calibration
3 ResNet-Calib + gradient 0.612 24.27 0.778 0.79 ✓ Certified ResNet for calibration, 2022
4 Instrument-CNN + gradient 0.608 23.84 0.763 0.82 ✓ Certified Instrument-specific CNN
5 MassSpecFormer + gradient 0.588 23.62 0.755 0.75 ✓ Certified Mass spectrometry transformer, 2024
6 Peak Fitting + gradient 0.578 22.98 0.73 0.78 ✓ Certified Gaussian peak fitting
7 DiffusionInstrumentation + gradient 0.564 21.83 0.683 0.86 ✓ Certified Zhang et al., 2024
8 PnP-BM3D + gradient 0.549 21.32 0.66 0.86 ✓ Certified Danielyan et al., 2012
9 Deconv + gradient 0.517 20.9 0.641 0.76 ✓ Certified Analytical baseline
10 ScoreInstrumentation + gradient 0.415 16.7 0.435 0.87 ✓ Certified Wei et al., 2025
11 PnP-NLM + gradient 0.415 16.96 0.448 0.83 ✓ Certified Non-local means filter

Dataset

Scenes: 5

Scoring Formula

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

PSNR: 40% SSIM: 40% Consistency: 20%
Back to X-ray Fluorescence Tomography