Hidden

MINFLUX Nanoscopy — Hidden Tier

(5 scenes)

Fully blind server-side evaluation — no data download.

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.

Parameter Specifications

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter Spec Range Unit
beam_center_error -0.7 – 2.3 nm
photon_count 290.0 – 1190.0 photons

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 ANNA-PALM + gradient 0.615 24.55 0.788 0.77 ✓ Certified Ouyang et al., Nat. Biotechnol. 2018
2 DECODE + gradient 0.605 23.97 0.767 0.79 ✓ Certified Speiser et al., Nat. Methods 2021
3 SPARCOM + gradient 0.598 23.86 0.764 0.77 ✓ Certified Solomon et al., SIAM J. Imaging Sci. 2019
4 MLE Localization + gradient 0.589 22.94 0.729 0.84 ✓ Certified Balzarotti et al., Science 2017

Dataset

Scenes: 5

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to MINFLUX Nanoscopy