Pump-Probe Microscopy

Pump-Probe 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
🥇 DynFormer 0.736 32.0 0.905 ✓ Certified Ultrafast dynamics transformer, 2024
🥈 TAS-Net 0.685 30.0 0.870 ✓ Certified Transient absorption DL, 2023
🥉 MCR-ALS 0.553 26.0 0.740 ✓ Certified Tauler, 1995
4 SVD-GlobFit 0.425 22.5 0.600 ✓ Certified van Stokkum et al., 2004

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
🥇 DynFormer + gradient 0.664
0.738
29.71 dB / 0.912
0.673
26.22 dB / 0.838
0.582
23.28 dB / 0.742
✓ Certified Ultrafast dynamics transformer, 2024
🥈 MCR-ALS + gradient 0.605
0.612
23.39 dB / 0.746
0.594
23.54 dB / 0.752
0.608
23.87 dB / 0.764
✓ Certified Tauler, Chemom. Intell. Lab. 1995
🥉 TAS-Net + gradient 0.546
0.704
27.65 dB / 0.873
0.515
20.4 dB / 0.618
0.420
17.39 dB / 0.470
✓ Certified Transient absorption DL, 2023
4 SVD-GlobFit + gradient 0.523
0.551
20.74 dB / 0.634
0.534
20.91 dB / 0.642
0.484
18.99 dB / 0.549
✓ Certified van Stokkum et al., BBA 2004

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 DynFormer + gradient 0.738 29.71 0.912
2 TAS-Net + gradient 0.704 27.65 0.873
3 MCR-ALS + gradient 0.612 23.39 0.746
4 SVD-GlobFit + gradient 0.551 20.74 0.634
Spec Ranges (4 parameters)
Parameter Min Max Unit
time_zero_drift -20.0 40.0 fs
pump_power_fluctuation -1.0 2.0 -
chirp_(gdd) -100.0 200.0 fs^2
spatial_overlap_error -4.0 8.0 -
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 DynFormer + gradient 0.673 26.22 0.838
2 MCR-ALS + gradient 0.594 23.54 0.752
3 SVD-GlobFit + gradient 0.534 20.91 0.642
4 TAS-Net + gradient 0.515 20.4 0.618
Spec Ranges (4 parameters)
Parameter Min Max Unit
time_zero_drift -24.0 36.0 fs
pump_power_fluctuation -1.2 1.8 -
chirp_(gdd) -120.0 180.0 fs^2
spatial_overlap_error -4.8 7.2 -
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 MCR-ALS + gradient 0.608 23.87 0.764
2 DynFormer + gradient 0.582 23.28 0.742
3 SVD-GlobFit + gradient 0.484 18.99 0.549
4 TAS-Net + gradient 0.420 17.39 0.47
Spec Ranges (4 parameters)
Parameter Min Max Unit
time_zero_drift -14.0 46.0 fs
pump_power_fluctuation -0.7 2.3 -
chirp_(gdd) -70.0 230.0 fs^2
spatial_overlap_error -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 → R → D

M Modulation
R Rotation
D Detector

Mismatch Parameters

Symbol Parameter Description Nominal Perturbed
t_d time_zero_drift Time-zero drift (fs) 0.0 20.0
p_p pump_power_fluctuation Pump power fluctuation (-) 0.0 1.0
c_( chirp_(gdd) Chirp (GDD) (fs^2) 0.0 100.0
s_o spatial_overlap_error Spatial overlap error (-) 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.