Quantum Illumination

Quantum Illumination

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
🥇 QuantumFormer 0.645 28.5 0.840 ✓ Certified Quantum detection transformer, 2024
🥈 QI-Net 0.582 26.5 0.780 ✓ Certified QI DL, 2023
🥉 FF-SFG 0.417 22.0 0.600 ✓ Certified Zhuang et al., PRL 2017
4 OPA Receiver 0.260 18.0 0.420 ✓ Certified Guha & Erkmen, PRA 2009

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
🥇 QuantumFormer + gradient 0.577
0.674
26.25 dB / 0.839
0.570
21.8 dB / 0.681
0.488
19.15 dB / 0.557
✓ Certified Quantum detection transformer, 2024
🥈 QI-Net + gradient 0.543
0.623
23.83 dB / 0.762
0.514
20.48 dB / 0.622
0.493
19.66 dB / 0.582
✓ Certified Quantum illumination DL, 2023
🥉 FF-SFG + gradient 0.487
0.494
19.01 dB / 0.550
0.507
19.99 dB / 0.598
0.461
18.18 dB / 0.509
✓ Certified Zhuang et al., PRL 2017
4 OPA Receiver + gradient 0.369
0.428
16.74 dB / 0.437
0.367
15.33 dB / 0.370
0.312
13.78 dB / 0.301
✓ Certified Guha & Erkmen, PRA 2009

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 QuantumFormer + gradient 0.674 26.25 0.839
2 QI-Net + gradient 0.623 23.83 0.762
3 FF-SFG + gradient 0.494 19.01 0.55
4 OPA Receiver + gradient 0.428 16.74 0.437
Spec Ranges (4 parameters)
Parameter Min Max Unit
entanglement_quality_(concurrence) 0.8 1.1 -
background_thermal_noise -20.0 40.0 -
detector_dark_count_rate -200.0 400.0 Hz
channel_loss -6.0 12.0 dB
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 QuantumFormer + gradient 0.570 21.8 0.681
2 QI-Net + gradient 0.514 20.48 0.622
3 FF-SFG + gradient 0.507 19.99 0.598
4 OPA Receiver + gradient 0.367 15.33 0.37
Spec Ranges (4 parameters)
Parameter Min Max Unit
entanglement_quality_(concurrence) 0.82 1.12 -
background_thermal_noise -24.0 36.0 -
detector_dark_count_rate -240.0 360.0 Hz
channel_loss -7.2 10.8 dB
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 QI-Net + gradient 0.493 19.66 0.582
2 QuantumFormer + gradient 0.488 19.15 0.557
3 FF-SFG + gradient 0.461 18.18 0.509
4 OPA Receiver + gradient 0.312 13.78 0.301
Spec Ranges (4 parameters)
Parameter Min Max Unit
entanglement_quality_(concurrence) 0.77 1.07 -
background_thermal_noise -14.0 46.0 -
detector_dark_count_rate -140.0 460.0 Hz
channel_loss -4.2 13.8 dB
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 → R → D

M Modulation
R Rotation
D Detector

Mismatch Parameters

Symbol Parameter Description Nominal Perturbed
e_q entanglement_quality_(concurrence) Entanglement quality (concurrence) (-) 1.0 0.9
b_t background_thermal_noise Background thermal noise (-) 0.0 20.0
d_d detector_dark_count_rate Detector dark count rate (Hz) 0.0 200.0
c_l channel_loss Channel loss (dB) 0.0 6.0

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.