Hidden

Coherent Anti-Stokes Raman (CARS) 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
pump_stokes_frequency_offset -0.7 – 2.3 cm^-1
non_resonant_background -7.0 – 23.0 -
chirp_mismatch -70.0 – 230.0 fs^2

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 FMDiff-CARS + gradient 0.733 29.86 0.915 0.84 ✓ Certified Li et al., NeurIPS 2024
2 SpecFormer-CARS + gradient 0.695 27.8 0.877 0.83 ✓ Certified Liao et al., Light Sci. Appl. 2023
3 ResNet-CARS + gradient 0.669 27.38 0.867 0.74 ✓ Certified Ying et al., Optica 2022
4 Diff-CARS + gradient 0.646 25.21 0.809 0.85 ✓ Certified Zhang et al., Nat. Methods 2024
5 PINN-CARS + gradient 0.644 25.7 0.823 0.79 ✓ Certified Bae et al., ACS Photonics 2021
6 MEM-CARS + gradient 0.586 22.82 0.724 0.84 ✓ Certified Rinia et al., J. Raman Spectrosc. 2008
7 CNN-NRB + gradient 0.558 22.36 0.705 0.76 ✓ Certified Houhou et al., Chem. Sci. 2020
8 U-Net-CARS + gradient 0.545 21.44 0.666 0.82 ✓ Certified Manifold et al., Nat. Mach. Intell. 2021
9 KK-Retrieval + gradient 0.540 21.77 0.68 0.75 ✓ Certified Liu et al., Opt. Express 2009

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 Coherent Anti-Stokes Raman (CARS) Microscopy