Public

Photoacoustic — 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
sos 1520.0 – 1580.0 1550.0 m/s
fluence -10.0 – 20.0 5.0 %
sensor_response -5.0 – 10.0 2.5 %

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

14.57 dB

SSIM 0.0990

Scenario II (Mismatch)

14.40 dB

SSIM 0.0397

Scenario III (Oracle)

14.08 dB

SSIM 0.0440

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 14.04 0.0090 13.60 0.0071 13.09 0.0073
scene_01 16.19 0.0131 16.08 0.0126 15.84 0.0100
scene_02 12.09 0.3322 12.36 0.1170 12.32 0.1422
scene_03 15.97 0.0415 15.59 0.0223 15.09 0.0167

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PAT-Former + gradient 0.764 31.37 0.935 0.88 ✓ Certified PAT reconstruction transformer, 2024
2 Deep-PAI + gradient 0.730 29.1 0.902 0.89 ✓ Certified Hauptmann et al., IEEE TMI 2018
3 PnP-ADMM + gradient 0.641 24.74 0.794 0.88 ✓ Certified Goudarzi et al., 2020
4 Universal Back-Proj + gradient 0.542 20.8 0.636 0.9 ✓ Certified Xu & Wang, Phys. Rev. E 2005

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 Photoacoustic