Hidden
Confocal 3D — Hidden Tier
(5 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 |
|---|---|---|
| z_step | -35.0 – 115.0 | nm |
| spherical_aberr | -0.07 – 0.23 | waves |
| refractive_index | 1.508 – 1.538 |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | SwinIR-3D + gradient | 0.733 | 30.02 | 0.917 | 0.83 | ✓ Certified | Liang et al., ICCV 2021 (3D adapted) |
| 2 | DiffusionMicro + gradient | 0.705 | 27.93 | 0.879 | 0.87 | ✓ Certified | Gao et al., Nat. Methods 2024 |
| 3 | Restormer-3D + gradient | 0.690 | 27.88 | 0.878 | 0.8 | ✓ Certified | Zamir et al., CVPR 2022 (3D adapted) |
| 4 | IRCNN-Confocal + gradient | 0.665 | 27.21 | 0.863 | 0.74 | ✓ Certified | Zhang et al., CVPR 2017 |
| 5 | Noise2Void + gradient | 0.612 | 23.87 | 0.764 | 0.84 | ✓ Certified | Krull et al., CVPR 2019 |
| 6 | Richardson-Lucy + gradient | 0.606 | 24.09 | 0.772 | 0.78 | ✓ Certified | Richardson, J. Opt. Soc. Am. 1972 |
| 7 | Wiener-3D + gradient | 0.605 | 24.22 | 0.776 | 0.76 | ✓ Certified | Wiener, 1942 |
| 8 | CARE + gradient | 0.580 | 23.37 | 0.745 | 0.74 | ✓ Certified | Weigert et al., Nat. Methods 2018 |
| 9 | U-Net-3D + gradient | 0.555 | 21.67 | 0.676 | 0.84 | ✓ Certified | Çiçek et al., MICCAI 2016 |
Dataset
Scenes: 5
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%