Wide-Angle X-ray Scattering (WAXS)

Wide-Angle X-ray Scattering (WAXS)

Join the Competition Contribute to Benchmark

Standard reconstruction benchmark — forward model perfectly known, no calibration needed. Score = 0.5 × clip((PSNR−15)/30, 0, 1) + 0.5 × SSIM

# Method Score PSNR (dB) SSIM Source
🥇 CrystalFormer 0.760 33.0 0.920 ✓ Certified Diffraction transformer, 2024
🥈 WAXS-Net 0.712 31.0 0.890 ✓ Certified WAXS pattern DL, 2023
🥉 Rietveld-WAXS 0.590 27.0 0.780 ✓ Certified Rietveld, 1969
4 PyFAI-Integrate 0.467 23.5 0.650 ✓ Certified Ashiotis et al., 2015

Dataset: PWM Benchmark (4 algorithms)

Blind Reconstruction Challenge — forward model has unknown mismatch, must calibrate from data. Score = 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

# Method Overall Score Public
PSNR / SSIM
 Dev
PSNR / SSIM
 Hidden
PSNR / SSIM
 Trust Source
🥇 CrystalFormer + gradient 0.681
0.754
30.73 dB / 0.927
0.672
26.25 dB / 0.839
0.616
24.68 dB / 0.792
✓ Certified Diffraction pattern transformer, 2024
🥈 Rietveld-WAXS + gradient 0.625
0.673
25.73 dB / 0.824
0.599
23.66 dB / 0.756
0.604
23.59 dB / 0.754
✓ Certified Rietveld, J. Appl. Cryst. 1969
🥉 WAXS-Net + gradient 0.623
0.749
29.74 dB / 0.913
0.570
22.16 dB / 0.697
0.549
21.75 dB / 0.679
✓ Certified WAXS pattern analysis DL, 2023
4 PyFAI-Integrate + gradient 0.534
0.546
20.91 dB / 0.642
0.553
21.74 dB / 0.679
0.502
20.45 dB / 0.620
✓ Certified Ashiotis et al., J. Appl. Cryst. 2015

Complete score requires all 3 tiers (Public + Dev + Hidden).

Join the competition →
Scoring: 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖) PSNR 40% · SSIM 40% · Consistency 20%
Public 5 scenes

Full-access development tier with all data visible.

What you get & how to use

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.

Public Leaderboard
# Method Score PSNR SSIM
1 CrystalFormer + gradient 0.754 30.73 0.927
2 WAXS-Net + gradient 0.749 29.74 0.913
3 Rietveld-WAXS + gradient 0.673 25.73 0.824
4 PyFAI-Integrate + gradient 0.546 20.91 0.642
Spec Ranges (4 parameters)
Parameter Min Max Unit
detector_distance_error -0.2 0.4 -
beam_center_error -0.6 1.2 px
polarization_correction 0.96 1.02 -
air_scatter_background -1.0 2.0 -
View Details →
Dev 5 scenes

Blind evaluation tier — no ground truth available.

What you get & how to use

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.

Dev Leaderboard
# Method Score PSNR SSIM
1 CrystalFormer + gradient 0.672 26.25 0.839
2 Rietveld-WAXS + gradient 0.599 23.66 0.756
3 WAXS-Net + gradient 0.570 22.16 0.697
4 PyFAI-Integrate + gradient 0.553 21.74 0.679
Spec Ranges (4 parameters)
Parameter Min Max Unit
detector_distance_error -0.24 0.36 -
beam_center_error -0.72 1.08 px
polarization_correction 0.964 1.024 -
air_scatter_background -1.2 1.8 -
Submit Reconstruction View Details →
Hidden 5 scenes

Fully blind server-side evaluation — no data download.

What you get & how to use

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.

Hidden Leaderboard
# Method Score PSNR SSIM
1 CrystalFormer + gradient 0.616 24.68 0.792
2 Rietveld-WAXS + gradient 0.604 23.59 0.754
3 WAXS-Net + gradient 0.549 21.75 0.679
4 PyFAI-Integrate + gradient 0.502 20.45 0.62
Spec Ranges (4 parameters)
Parameter Min Max Unit
detector_distance_error -0.14 0.46 -
beam_center_error -0.42 1.38 px
polarization_correction 0.954 1.014 -
air_scatter_background -0.7 2.3 -
Submit Algorithm View Details →

Blind Reconstruction Challenge

Challenge

Given measurements with unknown mismatch and spec ranges (not exact params), reconstruct the original signal. A method must be evaluated on all three tiers for a complete score. Scored on a composite metric: 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖).

Input

Measurements y, ideal forward model H, spec ranges

Output

Reconstructed signal x̂

Spec DAG — Forward Model Pipeline

R → D

R Rotation
D Detector

Mismatch Parameters

Symbol Parameter Description Nominal Perturbed
d_d detector_distance_error Detector distance error (-) 0.0 0.2
b_c beam_center_error Beam center error (px) 0.0 0.6
p_c polarization_correction Polarization correction (-) 1.0 0.98
a_s air_scatter_background Air scatter background (-) 0.0 1.0

Credits System

40%
Platform Profit Pool
Revenue allocated to benchmark rewards
30%
Winner Share
Top algorithm receives from pool
$100
Min Withdrawal
Minimum payout threshold
Spec Primitives Reference (11 primitives)
P Propagation

Free-space or medium propagation kernel (Fresnel, Rayleigh-Sommerfeld).

M Mask / Modulation

Spatial or spatio-temporal amplitude modulation (coded aperture, SLM pattern).

Π Projection

Geometric projection operator (Radon transform, fan-beam, cone-beam).

F Fourier Sampling

Sampling in the Fourier / k-space domain (MRI, ptychography).

C Convolution

Shift-invariant convolution with a point-spread function (PSF).

Σ Summation / Integration

Summation along a physical dimension (spectral, temporal, angular).

D Detector

Sensor readout with gain g and noise model η (Gaussian, Poisson, mixed).

S Structured Illumination

Patterned illumination (block, Hadamard, random) applied to the scene.

W Wavelength Dispersion

Spectral dispersion element (prism, grating) with shift α and aperture a.

R Rotation / Motion

Sample or gantry rotation (CT, electron tomography).

Λ Wavelength Selection

Spectral filter or monochromator selecting a wavelength band.