Phase Contrast Microscopy

Phase Contrast Microscopy

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 0.806 35.0 0.945 ✓ Certified Phase imaging transformer, 2024
🥈 QPI-Net 0.760 33.0 0.920 ✓ Certified Rivenson et al., 2019
🥉 DPC-ADMM 0.653 29.0 0.840 ✓ Certified Tian & Waller, BOE 2015
4 TIE Solver 0.535 25.5 0.720 ✓ Certified Teague, JOSA 1983

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 0.732
0.786
33.2 dB / 0.954
0.725
29.07 dB / 0.901
0.685
26.88 dB / 0.855
✓ Certified Phase imaging transformer, 2024
🥈 DPC-ADMM + gradient 0.640
0.679
26.17 dB / 0.837
0.632
24.44 dB / 0.784
0.608
23.35 dB / 0.745
✓ Certified Tian & Waller, BOE 2015
🥉 QPI-Net + gradient 0.612
0.753
30.51 dB / 0.924
0.600
23.31 dB / 0.743
0.482
19.73 dB / 0.586
✓ Certified Rivenson et al., Light: S&A 2019
4 TIE Solver + gradient 0.588
0.604
23.23 dB / 0.740
0.604
23.05 dB / 0.733
0.557
21.75 dB / 0.679
✓ Certified Teague, JOSA 1983

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 PhaseFormer + gradient 0.786 33.2 0.954
2 QPI-Net + gradient 0.753 30.51 0.924
3 DPC-ADMM + gradient 0.679 26.17 0.837
4 TIE Solver + gradient 0.604 23.23 0.74
Spec Ranges (3 parameters)
Parameter Min Max Unit
phase_ring_alignment -1.0 2.0 umoffset
halo_artifact_strength -0.06 0.12 relative
phase_ring_absorption 0.66 0.78 -
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 PhaseFormer + gradient 0.725 29.07 0.901
2 DPC-ADMM + gradient 0.632 24.44 0.784
3 TIE Solver + gradient 0.604 23.05 0.733
4 QPI-Net + gradient 0.600 23.31 0.743
Spec Ranges (3 parameters)
Parameter Min Max Unit
phase_ring_alignment -1.2 1.8 umoffset
halo_artifact_strength -0.072 0.108 relative
phase_ring_absorption 0.652 0.772 -
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 PhaseFormer + gradient 0.685 26.88 0.855
2 DPC-ADMM + gradient 0.608 23.35 0.745
3 TIE Solver + gradient 0.557 21.75 0.679
4 QPI-Net + gradient 0.482 19.73 0.586
Spec Ranges (3 parameters)
Parameter Min Max Unit
phase_ring_alignment -0.7 2.3 umoffset
halo_artifact_strength -0.042 0.138 relative
phase_ring_absorption 0.672 0.792 -
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

C → D

C Convolution
D Detector

Mismatch Parameters

Symbol Parameter Description Nominal Perturbed
p_r phase_ring_alignment Phase ring alignment (um offset) 0.0 1.0
h_a halo_artifact_strength Halo artifact strength (relative) 0.0 0.06
p_r phase_ring_absorption Phase ring absorption (-) 0.7 0.74

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.