Hidden
Streak Camera 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 |
|---|---|---|
| sweep_nonlinearity | -0.7 – 2.3 | - |
| temporal_resolution | 0.44 – 2.84 | ps |
| dynamic_range_saturation | -1.4 – 4.6 | - |
| trigger_jitter | -1.4 – 4.6 | ps |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | UltraFormer + gradient | 0.702 | 27.96 | 0.88 | 0.85 | ✓ Certified | Ultrafast transformer, 2024 |
| 2 | AL-DL + gradient | 0.601 | 24.16 | 0.774 | 0.75 | ✓ Certified | Yao et al., Photon. Res. 2021 |
| 3 | Temporal Filtering + gradient | 0.585 | 23.5 | 0.75 | 0.75 | ✓ Certified | Analytical baseline |
| 4 | Temporal-U-Net + gradient | 0.576 | 22.3 | 0.703 | 0.86 | ✓ Certified | 3D/Temporal U-Net variant |
| 5 | Unfolded-CUP + gradient | 0.573 | 22.47 | 0.71 | 0.82 | ✓ Certified | CUP algorithm unfolding |
| 6 | TwIST + gradient | 0.540 | 21.42 | 0.665 | 0.8 | ✓ Certified | Bioucas-Dias & Figueiredo, IEEE TIP 2007 |
| 7 | PnP-ADMM + gradient | 0.519 | 20.38 | 0.617 | 0.84 | ✓ Certified | ADMM + denoiser prior |
| 8 | PnP-FFDNet + gradient | 0.491 | 19.86 | 0.592 | 0.78 | ✓ Certified | Yuan et al., 2020 |
| 9 | CUP-Net + gradient | 0.485 | 19.63 | 0.581 | 0.78 | ✓ Certified | Parker et al., 2021 |
| 10 | ScoreUltrafast + gradient | 0.475 | 19.46 | 0.572 | 0.76 | ✓ Certified | Wei et al., 2025 |
| 11 | DiffusionUltrafast + gradient | 0.446 | 18.08 | 0.504 | 0.82 | ✓ Certified | Zhang et al., 2024 |
Dataset
Scenes: 5
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%