Dev

EBSD — Dev Tier

(3 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
pattern_center -2.4 – 3.6 pixels
sample_tilt 69.4 – 70.9 deg
detector_distance -0.6 – 0.9 mm

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PhysEBSD + gradient 0.766 32.05 0.943 0.84 ✓ Certified Chen et al., Acta Mater. 2024
2 SwinEBSD + gradient 0.745 29.91 0.915 0.9 ✓ Certified Li et al., npj Comput. Mater. 2023
3 TransEBSD + gradient 0.721 28.47 0.89 0.9 ✓ Certified Wang et al., Acta Mater. 2022
4 DiffEBSD + gradient 0.716 28.32 0.887 0.89 ✓ Certified Gao et al., NeurIPS 2024
5 PointEBSD + gradient 0.565 21.59 0.672 0.9 ✓ Certified Foden et al., Ultramicroscopy 2022
6 DnCNN-EBSD + gradient 0.555 21.32 0.66 0.89 ✓ Certified Kaufmann et al., npj Comput. Mater. 2020
7 DI-EBSD + gradient 0.545 21.18 0.654 0.86 ✓ Certified Chen et al., Ultramicroscopy 2015
8 TV-EBSD + gradient 0.493 19.37 0.568 0.86 ✓ Certified Wilkinson et al., Mater. Charact. 2006
9 Hough-EBSD + gradient 0.462 18.27 0.513 0.87 ✓ Certified Krieger Lassen, J. Microsc. 1994

Visible Data Fields

y H_ideal spec_ranges

Dataset

Format: HDF5
Scenes: 3

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to EBSD