Public
Interferometric SAR (InSAR) — Public Tier
(3 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 |
|---|---|---|---|
| phase_unwrapping_error | -1.0 – 2.0 | 0.5 | - |
| baseline_estimation_error | -0.2 – 0.4 | 0.1 | m |
| atmospheric_phase_screen | -0.2 – 0.4 | 0.1 | radrms |
| temporal_decorrelation | -0.06 – 0.12 | 0.03 | coherenceloss |
InverseNet Baseline Scores
Method: CPU_baseline — Mismatch parameter: nominal
Scenario I (Ideal)
6.46 dB
SSIM 0.2857
Scenario II (Mismatch)
8.06 dB
SSIM 0.2031
Scenario III (Oracle)
7.38 dB
SSIM 0.0149
Per-scene breakdown (4 scenes)
| Scene | PSNR I | SSIM I | PSNR II | SSIM II | PSNR III | SSIM III |
|---|---|---|---|---|---|---|
| scene_00 | 6.91 | 0.0044 | 6.65 | 0.0041 | 7.16 | 0.0048 |
| scene_01 | 5.53 | 0.1251 | 5.07 | 0.0617 | 6.77 | 0.0060 |
| scene_02 | 6.10 | 0.5340 | 8.82 | 0.3435 | 5.63 | 0.0250 |
| scene_03 | 7.29 | 0.4791 | 11.69 | 0.4033 | 9.97 | 0.0238 |
Public Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | InSAR-Former + gradient | 0.749 | 30.02 | 0.917 | 0.91 | ✓ Certified | InSAR phase transformer, 2024 |
| 2 | PhaseNet + gradient | 0.721 | 28.62 | 0.893 | 0.89 | ✓ Certified | Sica et al., IEEE TGRS 2021 |
| 3 | InSAR-BM3D + gradient | 0.645 | 24.9 | 0.799 | 0.88 | ✓ Certified | Deledalle et al., IEEE TIP 2015 |
| 4 | Goldstein-MCF + gradient | 0.526 | 20.16 | 0.606 | 0.91 | ✓ Certified | Goldstein et al., Radio Sci. 1988 |
Visible Data Fields
y
H_ideal
spec_ranges
x_true
true_spec
Dataset
Format: HDF5
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%