Dev

FTIR Spectroscopic Imaging — 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
wavenumber_calibration -0.48 – 0.72 cm^-1
water_vapor_absorption -0.15 – 0.15 -
detector_nonlinearity -1.2 – 1.8 -
atr_crystal_ri_error -0.24 – 0.36 -

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PINN-Spectra + gradient 0.693 27.82 0.877 0.82 ✓ Certified Physics-informed neural network
2 SpectraFormer + gradient 0.660 26.34 0.841 0.8 ✓ Certified Spectroscopy transformer, 2024
3 U-Net-Spectra + gradient 0.625 24.49 0.785 0.83 ✓ Certified Spectral U-Net variant
4 DiffusionSpectra + gradient 0.623 24.39 0.782 0.83 ✓ Certified Zhang et al., 2024
5 Cascade-UNet + gradient 0.615 23.91 0.765 0.85 ✓ Certified Physics-informed UNet, 2025
6 CDAE + gradient 0.614 23.51 0.751 0.89 ✓ Certified Zhang et al., Sensors 2024
7 PnP-DnCNN + gradient 0.597 23.26 0.741 0.84 ✓ Certified Zhang et al., 2017
8 Baseline Correction + gradient 0.560 22.24 0.7 0.79 ✓ Certified Polynomial fitting baseline
9 SVD + gradient 0.552 21.4 0.664 0.86 ✓ Certified Singular Value Decomposition
10 SG-ALS + gradient 0.550 21.71 0.677 0.81 ✓ Certified Savitzky-Golay + ALS baseline
11 ScoreSpectra + gradient 0.510 19.96 0.597 0.86 ✓ Certified Wei et al., 2025

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 FTIR Spectroscopic Imaging