Hidden
CASSI — Hidden Tier
(10 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 |
|---|---|---|
| mask_dx | 0.2 – 0.6 | px |
| mask_dy | 0.0 – 0.4 | px |
| mask_rotation | -0.05 – 0.15 | deg |
| dispersion_slope | 1.955 – 2.205 | px/band |
| dispersion_axis | -0.05 – 0.25 | deg |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | GAP-TV + gradient | 0.516 | 18.37 | 0.583 | 1.0 | ✓ Certified | PWM benchmark |
| 2 | SSR-L + gradient | 0.456 | 17.06 | 0.473 | 0.98 | ✓ Certified | PWM benchmark (CVPR 2024) |
| 3 | PnP-HSICNN + gradient | 0.455 | 15.59 | 0.518 | 0.96 | ✓ Certified | PWM benchmark |
| 4 | MST-L + gradient | 0.385 | 15.45 | 0.384 | 0.88 | ✓ Certified | PWM benchmark |
| 5 | HDNet + gradient | 0.280 | 10.96 | 0.373 | 0.61 | ✓ Certified | PWM benchmark |
Dataset
Scenes: 10
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%