Dev

FLIM — Dev Tier

(5 scenes)

Blind evaluation tier — no ground truth available.

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.

Parameter Specifications

🔒

True spec hidden — estimate parameters from spec ranges below.

Parameter Spec Range Unit
irf_width -24.0 – 36.0 ps
time_bin -6.0 – 9.0 ps
afterpulsing -0.006 – 0.009

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinFLIM + gradient 0.775 33.16 0.954 0.81 ✓ Certified Zhang et al., Biomed. Opt. Express 2023
2 PhysFLIM + gradient 0.745 30.41 0.923 0.86 ✓ Certified Chen et al., Nat. Photonics 2024
3 TransFLIM + gradient 0.728 29.72 0.912 0.83 ✓ Certified Wang et al., Nat. Methods 2022
4 DiffFLIM + gradient 0.727 29.06 0.901 0.88 ✓ Certified Gao et al., NeurIPS 2024
5 FLIMJ + gradient 0.650 25.15 0.807 0.88 ✓ Certified Li et al., Nat. Methods 2022
6 RLD-FLIM + gradient 0.647 25.72 0.824 0.8 ✓ Certified Ballew & Demas, Anal. Chem. 1989
7 DnCNN-FLIM + gradient 0.570 22.35 0.705 0.82 ✓ Certified Smith et al., Nat. Methods 2019
8 Phasor-FLIM + gradient 0.481 19.37 0.568 0.8 ✓ Certified Digman et al., Biophys. J. 2008
9 MLE-FLIM + gradient 0.391 15.87 0.395 0.87 ✓ Certified Grinvald & Steinberg, Anal. Biochem. 1974

Visible Data Fields

y H_ideal spec_ranges

Dataset

Format: HDF5
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