Public

Shearography — 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
shearing_amount_error -2.0 – 4.0 1.0 -
speckle_decorrelation -0.06 – 0.12 0.03 -
loading_non_uniformity -4.0 – 8.0 2.0 -

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

13.44 dB

SSIM 0.6187

Scenario II (Mismatch)

11.65 dB

SSIM 0.1994

Scenario III (Oracle)

19.78 dB

SSIM 0.1840

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 13.33 0.6172 12.92 0.1751 19.74 0.1812
scene_01 13.64 0.6232 10.08 0.2297 19.89 0.1827
scene_02 13.41 0.6172 11.17 0.2077 19.70 0.1891
scene_03 13.36 0.6172 12.44 0.1851 19.79 0.1829

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PhaseFormer + gradient 0.766 31.11 0.932 0.91 ✓ Certified Phase unwrapping transformer, 2024
2 ShearNet + gradient 0.764 30.69 0.927 0.93 ✓ Certified Shearography DL reconstruction, 2022
3 PnP-Phase + gradient 0.665 25.83 0.827 0.88 ✓ Certified PnP with phase unwrapping prior
4 Goldstein MCF + gradient 0.573 22.09 0.694 0.87 ✓ 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%
Back to Shearography