Hidden

SPC-Kronecker — Hidden Tier

(20 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
gain_decay_alpha 0.0035 – 0.0125 1/measurement
noise_sigma 0.02 – 0.06

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PnP-DRUNet + blind cal 0.687 24.75 0.776 0.9 ✓ Certified InverseNet Scenario IV
2 FISTA-TV (tuned) + blind cal 0.671 24.5 0.73 0.91 ✓ Certified InverseNet Scenario IV
3 FISTA-TV (paper) + blind cal 0.665 24.24 0.722 0.91 ✓ Certified InverseNet Scenario IV
4 HATNet + FISTA-TV + blind cal 0.665 24.53 0.72 0.9 ✓ Certified InverseNet Scenario IV
5 PnP-BM3D + blind cal 0.580 20.53 0.561 0.96 ✓ Certified InverseNet Scenario IV
6 ISTA-Net + blind cal 0.509 19.99 0.385 0.98 ✓ Certified InverseNet Scenario IV

Dataset

Scenes: 20

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to SPC-Kronecker