Public
Seismic Tomography — Public Tier
(5 scenes)Full-access development tier with all data visible.
What you get
Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.
How to use
Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.
What to submit
Reconstructed signals (x_hat) and corrected spec as HDF5.
Parameter Specifications
✓
True spec visible — use these exact values for Scenario III oracle reconstruction.
| Parameter | Spec Range | True Value | Unit |
|---|---|---|---|
| velocity_model_error | 4900.0 – 5200.0 | 5050.0 | m/s |
| source_location_error | -10.0 – 20.0 | 5.0 | m |
| receiver_coupling | 0.97 – 1.06 | 1.015 | - |
| timing_error | -0.0004 – 0.0008 | 0.0002 | s |
InverseNet Baseline Scores
Method: CPU_baseline — Mismatch parameter: nominal
Scenario I (Ideal)
7.77 dB
SSIM 0.3772
Scenario II (Mismatch)
7.61 dB
SSIM 0.1940
Scenario III (Oracle)
15.93 dB
SSIM 0.4222
Per-scene breakdown (4 scenes)
| Scene | PSNR I | SSIM I | PSNR II | SSIM II | PSNR III | SSIM III |
|---|---|---|---|---|---|---|
| scene_00 | 7.57 | 0.3615 | 7.48 | 0.1918 | 15.88 | 0.4337 |
| scene_01 | 7.70 | 0.3833 | 7.85 | 0.1983 | 15.89 | 0.4210 |
| scene_02 | 7.97 | 0.3846 | 7.45 | 0.1929 | 16.02 | 0.4175 |
| scene_03 | 7.84 | 0.3794 | 7.67 | 0.1931 | 15.94 | 0.4166 |
Public Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | ScoreExperimental + gradient | 0.782 | 31.69 | 0.939 | 0.95 | ✓ Certified | Wei et al., 2025 |
| 2 | SwinIR + gradient | 0.771 | 31.71 | 0.939 | 0.89 | ✓ Certified | Liang et al., ICCVW 2021 |
| 3 | Domain-Adapted-CNN + gradient | 0.763 | 30.93 | 0.93 | 0.91 | ✓ Certified | Domain adaptation CNN |
| 4 | DiffusionExperimental + gradient | 0.758 | 30.56 | 0.925 | 0.91 | ✓ Certified | Zhang et al., 2024 |
| 5 | ExpFormer + gradient | 0.750 | 30.74 | 0.927 | 0.86 | ✓ Certified | Experimental science transformer, 2024 |
| 6 | ResUNet + gradient | 0.743 | 29.64 | 0.911 | 0.91 | ✓ Certified | Residual U-Net baseline |
| 7 | PnP-RED + gradient | 0.680 | 26.34 | 0.841 | 0.9 | ✓ Certified | Romano et al., IEEE TIP 2017 |
| 8 | PnP-ADMM + gradient | 0.665 | 26.0 | 0.832 | 0.86 | ✓ Certified | ADMM + denoiser prior |
| 9 | Wiener Filter + gradient | 0.659 | 25.03 | 0.803 | 0.94 | ✓ Certified | Wiener filtering baseline |
| 10 | Tikhonov + gradient | 0.637 | 24.22 | 0.776 | 0.92 | ✓ Certified | Tikhonov, Doklady 1963 |
| 11 | Matched Filter + gradient | 0.631 | 24.24 | 0.777 | 0.89 | ✓ Certified | Optimal linear filter |
Visible Data Fields
y
H_ideal
spec_ranges
x_true
true_spec
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%