Hidden

Brillouin Microscopy — 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
brillouin_shift_calibration -7.0 – 23.0 MHz
vipa_fsr_error -0.07 – 0.23 -
elastic_scattering_leakage -13.8 – 4.2 -

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SpectraFormer + gradient 0.777 32.42 0.947 0.87 ✓ Certified Chen et al., arXiv 2023
2 DiffusionSpectra + gradient 0.736 30.83 0.929 0.78 ✓ Certified Gao et al., Nat. Methods 2024
3 CDAE + gradient 0.699 28.17 0.884 0.82 ✓ Certified Zhang et al., Sensors 2024
4 PINN-Brillouin + gradient 0.692 28.21 0.885 0.78 ✓ Certified Raissi et al., J. Comput. Phys. 2019 (adapted)
5 U-Net-Spectral + gradient 0.664 26.43 0.844 0.81 ✓ Certified Ronneberger et al., MICCAI 2015 (spectral)
6 SG-Baseline + gradient 0.608 23.71 0.758 0.84 ✓ Certified Savitzky & Golay, Anal. Chem. 1964
7 Lorentzian-Fit + gradient 0.566 22.74 0.721 0.75 ✓ Certified Dil, Rep. Prog. Phys. 1982
8 DnCNN-Brillouin + gradient 0.530 21.42 0.665 0.75 ✓ Certified Zhang et al., IEEE TIP 2017 (adapted)
9 CNN-Spectra + gradient 0.473 18.83 0.541 0.84 ✓ Certified Remer & Bhatt, Biomed. Opt. Express 2020

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 Brillouin Microscopy