Dev
Differential Interference Contrast (DIC) — Dev Tier
(5 scenes)Blind evaluation tier — no ground truth available.
What you get
Measurements (y), ideal forward operator (H), and spec ranges only.
How to use
Apply your pipeline from the Public tier. Use consistency as self-check.
What to submit
Reconstructed signals and corrected spec. Scored server-side.
Parameter Specifications
🔒
True spec hidden — estimate parameters from spec ranges below.
| Parameter | Spec Range | Unit |
|---|---|---|
| shear_amount | 76.0 – 136.0 | nm |
| bias_retardation | -0.15 – 0.15 | nm |
| prism_orientation | -0.72 – 1.08 | deg |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | SwinDIC + gradient | 0.763 | 32.12 | 0.944 | 0.82 | ✓ Certified | Liang et al., ICCV 2021 (DIC) |
| 2 | DiffusionDIC + gradient | 0.744 | 30.23 | 0.92 | 0.87 | ✓ Certified | Luo et al., Nat. Photonics 2023 (DIC) |
| 3 | PhysPhase-Net + gradient | 0.700 | 28.68 | 0.894 | 0.78 | ✓ Certified | Barbastathis et al., Optica 2019 |
| 4 | PhaseNet-DIC + gradient | 0.650 | 25.95 | 0.831 | 0.79 | ✓ Certified | Sinha et al., Optica 2020 |
| 5 | PnP-DIC + gradient | 0.645 | 25.72 | 0.824 | 0.79 | ✓ Certified | Kamilov et al., Optica 2017 (DIC) |
| 6 | DIC-CNN + gradient | 0.637 | 24.55 | 0.788 | 0.88 | ✓ Certified | Rivenson et al., Optica 2018 |
| 7 | Phase-DLSIM + gradient | 0.582 | 22.81 | 0.724 | 0.82 | ✓ Certified | Stephens & Allen, J. Biomed. Opt. 2003 |
| 8 | DIC-Deconv + gradient | 0.559 | 22.1 | 0.694 | 0.8 | ✓ Certified | Preza et al., JOSA A 1999 |
| 9 | TV-DIC + gradient | 0.512 | 20.42 | 0.619 | 0.8 | ✓ Certified | Bostan et al., IEEE TIP 2014 |
Visible Data Fields
y
H_ideal
spec_ranges
Dataset
Format: HDF5
Scenes: 5
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%