MINFLUX Nanoscopy

MINFLUX Nanoscopy

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
🥇 ANNA-PALM 0.778 33.08 0.953 ✓ Certified Ouyang et al., Nat. Biotechnol. 2018
🥈 DECODE 0.743 32.1 0.915 ✓ Certified Speiser et al., Nat. Methods 2021
🥉 SPARCOM 0.677 28.76 0.896 ✓ Certified Solomon et al., SIAM J. Imaging Sci. 2019
4 MLE Localization 0.665 28.28 0.887 ✓ Certified Balzarotti et al., Science 2017

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
🥇 ANNA-PALM + gradient 0.672
0.759
31.2 dB / 0.933
0.642
24.95 dB / 0.801
0.615
24.55 dB / 0.788
✓ Certified Ouyang et al., Nat. Biotechnol. 2018
🥈 DECODE + gradient 0.667
0.764
30.7 dB / 0.927
0.631
24.99 dB / 0.802
0.605
23.97 dB / 0.767
✓ Certified Speiser et al., Nat. Methods 2021
🥉 MLE Localization + gradient 0.649
0.701
27.2 dB / 0.863
0.658
25.75 dB / 0.825
0.589
22.94 dB / 0.729
✓ Certified Balzarotti et al., Science 2017
4 SPARCOM + gradient 0.641
0.704
27.13 dB / 0.861
0.620
24.69 dB / 0.792
0.598
23.86 dB / 0.764
✓ Certified Solomon et al., SIAM J. Imaging Sci. 2019

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 DECODE + gradient 0.764 30.7 0.927
2 ANNA-PALM + gradient 0.759 31.2 0.933
3 SPARCOM + gradient 0.704 27.13 0.861
4 MLE Localization + gradient 0.701 27.2 0.863
Spec Ranges (2 parameters)
Parameter Min Max Unit
beam_center_error -1.0 2.0 nm
photon_count 200.0 1100.0 photons
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 MLE Localization + gradient 0.658 25.75 0.825
2 ANNA-PALM + gradient 0.642 24.95 0.801
3 DECODE + gradient 0.631 24.99 0.802
4 SPARCOM + gradient 0.620 24.69 0.792
Spec Ranges (2 parameters)
Parameter Min Max Unit
beam_center_error -1.2 1.8 nm
photon_count 140.0 1040.0 photons
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 ANNA-PALM + gradient 0.615 24.55 0.788
2 DECODE + gradient 0.605 23.97 0.767
3 SPARCOM + gradient 0.598 23.86 0.764
4 MLE Localization + gradient 0.589 22.94 0.729
Spec Ranges (2 parameters)
Parameter Min Max Unit
beam_center_error -0.7 2.3 nm
photon_count 290.0 1190.0 photons
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
b_c beam_center_error Beam center error (nm) 0.0 1.0
p_c photon_count Photon count (photons) 500.0 800.0

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.