Hidden

Photoacoustic — Hidden Tier

(3 scenes)

Fully blind server-side evaluation — no data download.

What you get

No data downloadable. Algorithm runs server-side on hidden measurements.

How to use

Package algorithm as Docker container / Python script. Submit via link.

What to submit

Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

Parameter Specifications

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter Spec Range Unit
sos 1526.0 – 1586.0 m/s
fluence -7.0 – 23.0 %
sensor_response -3.5 – 11.5 %

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PAT-Former + gradient 0.601 23.19 0.738 0.87 ✓ Certified PAT reconstruction transformer, 2024
2 Universal Back-Proj + gradient 0.545 21.58 0.672 0.8 ✓ Certified Xu & Wang, Phys. Rev. E 2005
3 Deep-PAI + gradient 0.520 20.55 0.625 0.82 ✓ Certified Hauptmann et al., IEEE TMI 2018
4 PnP-ADMM + gradient 0.410 17.4 0.47 0.74 ✓ Certified Goudarzi et al., 2020

Dataset

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