Dev

Stimulated Raman Scattering (SRS) Microscopy — 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
lock_in_phase_error -2.4 – 3.6 deg
cross_phase_modulation -1.2 – 1.8 -
laser_intensity_noise_(rin) -152.4 – -146.4 dBc/Hz

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SpectraFormer + gradient 0.630 24.37 0.781 0.87 ✓ Certified Spectroscopy transformer, 2024
2 CDAE + gradient 0.628 24.88 0.798 0.8 ✓ Certified Zhang et al., Sensors 2024
3 PnP-DnCNN + gradient 0.609 23.42 0.747 0.88 ✓ Certified Zhang et al., 2017
4 Cascade-UNet + gradient 0.602 23.88 0.764 0.79 ✓ Certified Physics-informed UNet, 2025
5 PINN-Spectra + gradient 0.600 23.24 0.74 0.86 ✓ Certified Physics-informed neural network
6 DiffusionSpectra + gradient 0.568 22.44 0.708 0.8 ✓ Certified Zhang et al., 2024
7 ScoreSpectra + gradient 0.562 21.79 0.681 0.86 ✓ Certified Wei et al., 2025
8 SVD + gradient 0.547 21.68 0.676 0.8 ✓ Certified Singular Value Decomposition
9 SG-ALS + gradient 0.547 21.68 0.676 0.8 ✓ Certified Savitzky-Golay + ALS baseline
10 Baseline Correction + gradient 0.536 20.86 0.639 0.86 ✓ Certified Polynomial fitting baseline
11 U-Net-Spectra + gradient 0.510 19.95 0.596 0.86 ✓ Certified Spectral U-Net variant

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 Stimulated Raman Scattering (SRS) Microscopy