Hidden
Adaptive Optics (AO) Imaging — 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 |
|---|---|---|
| dm_actuator_gain | 0.986 – 1.046 | - |
| wfs_centroid_bias | -0.028 – 0.092 | px |
| fried_parameter_r0 | 0.136 – 0.196 | m |
| servo_lag | -0.28 – 0.92 | ms |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | AO-ViT + gradient | 0.645 | 25.09 | 0.805 | 0.86 | ✓ Certified | Vision transformer for AO, 2024 |
| 2 | AO-Transformer + gradient | 0.581 | 22.48 | 0.71 | 0.86 | ✓ Certified | Wavefront sensing transformer, 2023 |
| 3 | WFNet + gradient | 0.571 | 22.63 | 0.716 | 0.79 | ✓ Certified | Nishizaki et al., Opt. Express 2019 |
| 4 | LIFT-Net + gradient | 0.563 | 22.7 | 0.719 | 0.74 | ✓ Certified | Orban de Xivry et al., MNRAS 2021 |
| 5 | DiffusionAO + gradient | 0.562 | 21.83 | 0.683 | 0.85 | ✓ Certified | Score-based diffusion for wavefront reconstruction, 2024 |
| 6 | PnP-ADMM (WF) + gradient | 0.489 | 19.52 | 0.575 | 0.82 | ✓ Certified | Venkatakrishnan et al., 2013 |
| 7 | Fried Estimator + gradient | 0.484 | 19.07 | 0.553 | 0.86 | ✓ Certified | Fried, JOSA 1977 |
| 8 | Zernike LS + gradient | 0.462 | 18.48 | 0.524 | 0.84 | ✓ Certified | Noll, JOSA 1976 |
Dataset
Scenes: 5
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%