Dev
Raman Imaging / 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 |
|---|---|---|
| spectral_calibration_shift | -0.48 – 0.72 | cm^-1 |
| fluorescence_background | -2.4 – 3.6 | relative |
| laser_power_fluctuation | -1.2 – 1.8 | - |
| cosmic_ray_artifact | -0.24 – 0.36 | - |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | Cascade-UNet + gradient | 0.677 | 26.7 | 0.851 | 0.85 | ✓ Certified | Physics-informed UNet, 2025 |
| 2 | U-Net-Spectra + gradient | 0.660 | 26.27 | 0.839 | 0.81 | ✓ Certified | Spectral U-Net variant |
| 3 | SVD + gradient | 0.634 | 24.67 | 0.792 | 0.85 | ✓ Certified | Singular Value Decomposition |
| 4 | SpectraFormer + gradient | 0.625 | 24.76 | 0.794 | 0.8 | ✓ Certified | Spectroscopy transformer, 2024 |
| 5 | PINN-Spectra + gradient | 0.609 | 23.9 | 0.765 | 0.82 | ✓ Certified | Physics-informed neural network |
| 6 | PnP-DnCNN + gradient | 0.594 | 23.47 | 0.749 | 0.8 | ✓ Certified | Zhang et al., 2017 |
| 7 | ScoreSpectra + gradient | 0.590 | 23.32 | 0.743 | 0.8 | ✓ Certified | Wei et al., 2025 |
| 8 | CDAE + gradient | 0.567 | 21.75 | 0.679 | 0.89 | ✓ Certified | Zhang et al., Sensors 2024 |
| 9 | Baseline Correction + gradient | 0.556 | 21.79 | 0.681 | 0.83 | ✓ Certified | Polynomial fitting baseline |
| 10 | DiffusionSpectra + gradient | 0.514 | 20.08 | 0.603 | 0.86 | ✓ Certified | Zhang et al., 2024 |
| 11 | SG-ALS + gradient | 0.511 | 19.97 | 0.597 | 0.86 | ✓ Certified | Savitzky-Golay + ALS baseline |
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%