Public
Ocean Acoustic 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 |
|---|---|---|---|
| sound_speed_profile_error | -0.4 – 0.8 | 0.2 | - |
| multipath_identification | -4.0 – 8.0 | 2.0 | - |
| source/receiver_position | -2.0 – 4.0 | 1.0 | m |
| current_velocity_error | -0.1 – 0.2 | 0.05 | m/s |
InverseNet Baseline Scores
Method: CPU_baseline — Mismatch parameter: nominal
Scenario I (Ideal)
7.77 dB
SSIM 0.3772
Scenario II (Mismatch)
7.65 dB
SSIM 0.2288
Scenario III (Oracle)
16.34 dB
SSIM 0.4542
Per-scene breakdown (4 scenes)
| Scene | PSNR I | SSIM I | PSNR II | SSIM II | PSNR III | SSIM III |
|---|---|---|---|---|---|---|
| scene_00 | 7.57 | 0.3615 | 7.52 | 0.2249 | 16.28 | 0.4660 |
| scene_01 | 7.70 | 0.3833 | 7.81 | 0.2328 | 16.28 | 0.4522 |
| scene_02 | 7.97 | 0.3846 | 7.55 | 0.2285 | 16.43 | 0.4500 |
| scene_03 | 7.84 | 0.3794 | 7.72 | 0.2289 | 16.35 | 0.4487 |
Public Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | DiffusionExperimental + gradient | 0.797 | 33.15 | 0.954 | 0.92 | ✓ Certified | Zhang et al., 2024 |
| 2 | SwinIR + gradient | 0.772 | 32.07 | 0.943 | 0.87 | ✓ Certified | Liang et al., ICCVW 2021 |
| 3 | ResUNet + gradient | 0.772 | 31.26 | 0.934 | 0.93 | ✓ Certified | Residual U-Net baseline |
| 4 | Domain-Adapted-CNN + gradient | 0.767 | 31.69 | 0.939 | 0.87 | ✓ Certified | Domain adaptation CNN |
| 5 | ScoreExperimental + gradient | 0.764 | 30.97 | 0.93 | 0.91 | ✓ Certified | Wei et al., 2025 |
| 6 | ExpFormer + gradient | 0.732 | 28.98 | 0.9 | 0.91 | ✓ Certified | Experimental science transformer, 2024 |
| 7 | PnP-ADMM + gradient | 0.686 | 26.51 | 0.846 | 0.91 | ✓ Certified | ADMM + denoiser prior |
| 8 | PnP-RED + gradient | 0.681 | 26.5 | 0.846 | 0.89 | ✓ Certified | Romano et al., IEEE TIP 2017 |
| 9 | Tikhonov + gradient | 0.638 | 24.28 | 0.778 | 0.92 | ✓ Certified | Tikhonov, Doklady 1963 |
| 10 | Matched Filter + gradient | 0.605 | 23.1 | 0.735 | 0.9 | ✓ Certified | Optimal linear filter |
| 11 | Wiener Filter + gradient | 0.603 | 23.1 | 0.735 | 0.89 | ✓ Certified | Wiener filtering baseline |
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%