Public

Small-Angle X-ray Scattering (SAXS) — Public Tier

(5 scenes)

Full-access development tier with all data visible.

What you get

Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.

How to use

Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.

What to submit

Reconstructed signals (x_hat) and corrected spec as HDF5.

Parameter Specifications

✓

True spec visible — use these exact values for Scenario III oracle reconstruction.

Parameter Spec Range True Value Unit
sample_detector_distance 998.0 – 1004.0 1001.0 mm
beam_center_x -0.4 – 0.8 0.2 px
beam_center_y -0.4 – 0.8 0.2 px
wavelength_error -0.0002 – 0.0004 0.0001 nm

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

18.40 dB

SSIM 0.3184

Scenario II (Mismatch)

18.40 dB

SSIM 0.3242

Scenario III (Oracle)

23.39 dB

SSIM 0.7172

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 17.46 0.3125 17.46 0.3176 22.43 0.7138
scene_01 17.16 0.3063 17.16 0.3121 22.13 0.7054
scene_02 19.64 0.3404 19.64 0.3450 24.65 0.7297
scene_03 19.34 0.3145 19.34 0.3221 24.35 0.7199

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 ScatterFormer + gradient 0.765 31.7 0.939 0.86 ✓ Certified Scattering analysis transformer, 2024
2 ScatterNet + gradient 0.757 30.41 0.923 0.92 ✓ Certified Franke et al., Biophys. J. 2018
3 McSAS + gradient 0.642 24.53 0.787 0.91 ✓ Certified Bressler et al., J. Appl. Cryst. 2015
4 PyFAI-Integrate + gradient 0.565 21.73 0.678 0.88 ✓ Certified Ashiotis et al., J. Appl. Cryst. 2015

Visible Data Fields

y H_ideal spec_ranges x_true true_spec

Dataset

Format: HDF5
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 Small-Angle X-ray Scattering (SAXS)