Hidden
Atom Probe Tomography (APT) — 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 |
|---|---|---|
| flight_path_error | -0.07 – 0.23 | mm |
| voltage_calibration | 0.9972 – 1.0092 | - |
| detection_efficiency | 0.586 – 0.646 | - |
| tip_radius_error | -0.7 – 2.3 | nm |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | EquivAPT + gradient | 0.734 | 30.87 | 0.929 | 0.77 | ✓ Certified | Adapted from equivariant vision transformer for atomic imaging, 2025 |
| 2 | DiffusionAPT + gradient | 0.684 | 26.95 | 0.857 | 0.86 | ✓ Certified | Inspired by Chung et al., ICLR 2023 (score-based MRI) |
| 3 | APT-Former + gradient | 0.613 | 24.5 | 0.786 | 0.77 | ✓ Certified | Moody et al., Microsc. Microanal. 30(2):341, 2024 |
| 4 | TrajectoryPINN + gradient | 0.565 | 21.81 | 0.682 | 0.87 | ✓ Certified | De Geuser & Gault, Annu. Rev. Mater. Res. 52:1, 2022 |
| 5 | Tikhonov-Trajectory + gradient | 0.515 | 20.67 | 0.63 | 0.78 | ✓ Certified | Geiser et al., Microsc. Microanal. 13(6):437, 2007 |
| 6 | LISTA-APT + gradient | 0.513 | 20.46 | 0.621 | 0.8 | ✓ Certified | Gregor & LeCun, ICML 2010; adapted for APT 2020 |
| 7 | ResNet-ArtefactCorr + gradient | 0.495 | 19.37 | 0.568 | 0.87 | ✓ Certified | Wei et al., Ultramicroscopy 206:112817, 2019 |
| 8 | Bas-Protocol + gradient | 0.411 | 17.18 | 0.459 | 0.78 | ✓ Certified | Bas et al., Appl. Surf. Sci. 87-88:298, 1995 |
| 9 | PnP-BM3D (APT) + gradient | 0.387 | 16.56 | 0.428 | 0.75 | ✓ Certified | Danielyan et al., IEEE TIP 21(9):3884, 2012 |
Dataset
Scenes: 5
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%