Hidden
Fundus — 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 |
|---|---|---|
| pupil_dilation | -0.35 – 1.15 | mm |
| focus | -0.175 – 0.575 | diopters |
| vignetting | -3.5 – 11.5 | % |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | PnP-BM3D + gradient | 0.590 | 23.55 | 0.752 | 0.77 | ✓ Certified | Danielyan et al., 2012 |
| 2 | Swin-Fundus + gradient | 0.585 | 23.49 | 0.75 | 0.75 | ✓ Certified | Li et al., IEEE TMI 2023 |
| 3 | cofe-Net + gradient | 0.584 | 23.32 | 0.743 | 0.77 | ✓ Certified | Shen et al., IEEE TMI 2020 |
| 4 | Richardson-Lucy + gradient | 0.528 | 20.72 | 0.633 | 0.84 | ✓ Certified | Richardson 1972 / Lucy 1974 |
Dataset
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%