Dev
Brillouin 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 |
|---|---|---|
| brillouin_shift_calibration | -12.0 – 18.0 | MHz |
| vipa_fsr_error | -0.12 – 0.18 | - |
| elastic_scattering_leakage | -10.8 – 7.2 | - |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | SpectraFormer + gradient | 0.817 | 35.81 | 0.972 | 0.85 | ✓ Certified | Chen et al., arXiv 2023 |
| 2 | DiffusionSpectra + gradient | 0.756 | 31.1 | 0.932 | 0.86 | ✓ Certified | Gao et al., Nat. Methods 2024 |
| 3 | PINN-Brillouin + gradient | 0.736 | 30.47 | 0.924 | 0.81 | ✓ Certified | Raissi et al., J. Comput. Phys. 2019 (adapted) |
| 4 | CDAE + gradient | 0.700 | 27.68 | 0.874 | 0.87 | ✓ Certified | Zhang et al., Sensors 2024 |
| 5 | U-Net-Spectral + gradient | 0.693 | 27.17 | 0.862 | 0.88 | ✓ Certified | Ronneberger et al., MICCAI 2015 (spectral) |
| 6 | SG-Baseline + gradient | 0.642 | 24.79 | 0.795 | 0.88 | ✓ Certified | Savitzky & Golay, Anal. Chem. 1964 |
| 7 | DnCNN-Brillouin + gradient | 0.610 | 24.1 | 0.772 | 0.8 | ✓ Certified | Zhang et al., IEEE TIP 2017 (adapted) |
| 8 | Lorentzian-Fit + gradient | 0.598 | 22.99 | 0.731 | 0.88 | ✓ Certified | Dil, Rep. Prog. Phys. 1982 |
| 9 | CNN-Spectra + gradient | 0.570 | 22.0 | 0.69 | 0.87 | ✓ Certified | Remer & Bhatt, Biomed. Opt. Express 2020 |
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%