Hidden
EBSD — 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 |
|---|---|---|
| pattern_center | -1.4 – 4.6 | pixels |
| sample_tilt | 69.65 – 71.15 | deg |
| detector_distance | -0.35 – 1.15 | mm |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | PhysEBSD + gradient | 0.725 | 30.26 | 0.921 | 0.77 | ✓ Certified | Chen et al., Acta Mater. 2024 |
| 2 | SwinEBSD + gradient | 0.686 | 27.04 | 0.859 | 0.86 | ✓ Certified | Li et al., npj Comput. Mater. 2023 |
| 3 | DiffEBSD + gradient | 0.676 | 26.93 | 0.856 | 0.82 | ✓ Certified | Gao et al., NeurIPS 2024 |
| 4 | TransEBSD + gradient | 0.618 | 24.02 | 0.769 | 0.85 | ✓ Certified | Wang et al., Acta Mater. 2022 |
| 5 | DI-EBSD + gradient | 0.546 | 21.15 | 0.652 | 0.87 | ✓ Certified | Chen et al., Ultramicroscopy 2015 |
| 6 | DnCNN-EBSD + gradient | 0.492 | 19.34 | 0.567 | 0.86 | ✓ Certified | Kaufmann et al., npj Comput. Mater. 2020 |
| 7 | PointEBSD + gradient | 0.471 | 18.82 | 0.541 | 0.83 | ✓ Certified | Foden et al., Ultramicroscopy 2022 |
| 8 | Hough-EBSD + gradient | 0.440 | 17.67 | 0.484 | 0.85 | ✓ Certified | Krieger Lassen, J. Microsc. 1994 |
| 9 | TV-EBSD + gradient | 0.430 | 18.08 | 0.504 | 0.74 | ✓ Certified | Wilkinson et al., Mater. Charact. 2006 |
Dataset
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%