Hidden
SPC-Block — Hidden Tier
(11 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 | ISTA-Net + gradient | 0.614 | 22.81 | 0.663 | 0.83 | ✓ Certified | InverseNet baseline |
| 2 | HATNet + gradient | 0.612 | 22.51 | 0.696 | 0.77 | ✓ Certified | InverseNet baseline |
| 3 | FISTA-TV + gradient | 0.600 | 21.74 | 0.659 | 0.81 | ✓ Certified | InverseNet baseline |
| 4 | PnP-DRUNet + gradient | 0.537 | 19.68 | 0.53 | 0.84 | ✓ Certified | InverseNet baseline |
Dataset
Scenes: 11
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%