Dev
Ocean Acoustic Tomography — 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 |
|---|---|---|
| sound_speed_profile_error | -0.48 – 0.72 | - |
| multipath_identification | -4.8 – 7.2 | - |
| source/receiver_position | -2.4 – 3.6 | m |
| current_velocity_error | -0.12 – 0.18 | m/s |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | SwinIR + gradient | 0.701 | 28.6 | 0.893 | 0.79 | ✓ Certified | Liang et al., ICCVW 2021 |
| 2 | Domain-Adapted-CNN + gradient | 0.693 | 27.84 | 0.877 | 0.82 | ✓ Certified | Domain adaptation CNN |
| 3 | ScoreExperimental + gradient | 0.668 | 26.65 | 0.849 | 0.81 | ✓ Certified | Wei et al., 2025 |
| 4 | DiffusionExperimental + gradient | 0.652 | 25.42 | 0.815 | 0.86 | ✓ Certified | Zhang et al., 2024 |
| 5 | ExpFormer + gradient | 0.632 | 24.28 | 0.778 | 0.89 | ✓ Certified | Experimental science transformer, 2024 |
| 6 | PnP-RED + gradient | 0.627 | 24.65 | 0.791 | 0.82 | ✓ Certified | Romano et al., IEEE TIP 2017 |
| 7 | ResUNet + gradient | 0.625 | 24.42 | 0.783 | 0.84 | ✓ Certified | Residual U-Net baseline |
| 8 | Matched Filter + gradient | 0.612 | 23.8 | 0.761 | 0.85 | ✓ Certified | Optimal linear filter |
| 9 | Tikhonov + gradient | 0.581 | 22.41 | 0.707 | 0.87 | ✓ Certified | Tikhonov, Doklady 1963 |
| 10 | PnP-ADMM + gradient | 0.570 | 22.52 | 0.712 | 0.8 | ✓ Certified | ADMM + denoiser prior |
| 11 | Wiener Filter + gradient | 0.554 | 21.86 | 0.684 | 0.81 | ✓ Certified | Wiener filtering 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%