Hidden

FLIM — 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
irf_width -14.0 – 46.0 ps
time_bin -3.5 – 11.5 ps
afterpulsing -0.0035 – 0.0115

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinFLIM + gradient 0.741 31.31 0.935 0.77 ✓ Certified Zhang et al., Biomed. Opt. Express 2023
2 PhysFLIM + gradient 0.703 29.04 0.901 0.76 ✓ Certified Chen et al., Nat. Photonics 2024
3 DiffFLIM + gradient 0.685 27.71 0.875 0.79 ✓ Certified Gao et al., NeurIPS 2024
4 RLD-FLIM + gradient 0.635 25.2 0.808 0.8 ✓ Certified Ballew & Demas, Anal. Chem. 1989
5 TransFLIM + gradient 0.634 24.79 0.795 0.84 ✓ Certified Wang et al., Nat. Methods 2022
6 FLIMJ + gradient 0.614 23.76 0.76 0.86 ✓ Certified Li et al., Nat. Methods 2022
7 DnCNN-FLIM + gradient 0.473 19.25 0.562 0.78 ✓ Certified Smith et al., Nat. Methods 2019
8 Phasor-FLIM + gradient 0.450 18.41 0.52 0.79 ✓ Certified Digman et al., Biophys. J. 2008
9 MLE-FLIM + gradient 0.309 13.8 0.302 0.75 ✓ Certified Grinvald & Steinberg, Anal. Biochem. 1974

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 FLIM