Shearography

Shearography

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
🥇 PhaseFormer 0.784 34.0 0.935 ✓ Certified Phase unwrapping transformer, 2024
🥈 ShearNet 0.733 32.0 0.900 ✓ Certified Shearography DL, 2022
🥉 PnP-Phase 0.617 28.0 0.800 ✓ Certified PnP phase unwrapping
4 Goldstein MCF 0.485 24.0 0.670 ✓ Certified Goldstein et al., 1988

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
🥇 PhaseFormer + gradient 0.687
0.766
31.11 dB / 0.932
0.688
27.67 dB / 0.874
0.608
24.2 dB / 0.776
✓ Certified Phase unwrapping transformer, 2024
🥈 ShearNet + gradient 0.665
0.764
30.69 dB / 0.927
0.631
25.0 dB / 0.802
0.601
23.82 dB / 0.762
✓ Certified Shearography DL reconstruction, 2022
🥉 PnP-Phase + gradient 0.583
0.665
25.83 dB / 0.827
0.563
21.73 dB / 0.678
0.522
20.91 dB / 0.642
✓ Certified PnP with phase unwrapping prior
4 Goldstein MCF + gradient 0.538
0.573
22.09 dB / 0.694
0.548
20.99 dB / 0.645
0.494
19.47 dB / 0.573
✓ Certified Goldstein et al., Radio Sci. 1988

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 3 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 PhaseFormer + gradient 0.766 31.11 0.932
2 ShearNet + gradient 0.764 30.69 0.927
3 PnP-Phase + gradient 0.665 25.83 0.827
4 Goldstein MCF + gradient 0.573 22.09 0.694
Spec Ranges (3 parameters)
Parameter Min Max Unit
shearing_amount_error -2.0 4.0 -
speckle_decorrelation -0.06 0.12 -
loading_non_uniformity -4.0 8.0 -
View Details →
Dev 3 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 PhaseFormer + gradient 0.688 27.67 0.874
2 ShearNet + gradient 0.631 25.0 0.802
3 PnP-Phase + gradient 0.563 21.73 0.678
4 Goldstein MCF + gradient 0.548 20.99 0.645
Spec Ranges (3 parameters)
Parameter Min Max Unit
shearing_amount_error -2.4 3.6 -
speckle_decorrelation -0.072 0.108 -
loading_non_uniformity -4.8 7.2 -
Submit Reconstruction View Details →
Hidden 3 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 PhaseFormer + gradient 0.608 24.2 0.776
2 ShearNet + gradient 0.601 23.82 0.762
3 PnP-Phase + gradient 0.522 20.91 0.642
4 Goldstein MCF + gradient 0.494 19.47 0.573
Spec Ranges (3 parameters)
Parameter Min Max Unit
shearing_amount_error -1.4 4.6 -
speckle_decorrelation -0.042 0.138 -
loading_non_uniformity -2.8 9.2 -
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

M → P → D

M Modulation
P Propagation
D Detector

Mismatch Parameters

Symbol Parameter Description Nominal Perturbed
s_a shearing_amount_error Shearing amount error (-) 0.0 2.0
s_d speckle_decorrelation Speckle decorrelation (-) 0.0 0.06
l_n loading_non_uniformity Loading non-uniformity (-) 0.0 4.0

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.