Public

Cryo-Electron Tomography (Cryo-ET) — Public Tier

(3 scenes)

Full-access development tier with all data visible.

What you get

Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.

How to use

Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.

What to submit

Reconstructed signals (x_hat) and corrected spec as HDF5.

Parameter Specifications

✓

True spec visible — use these exact values for Scenario III oracle reconstruction.

Parameter Spec Range True Value Unit
tilt_axis_offset -0.6 – 1.2 0.3 px
tilt_angle_accuracy -0.2 – 0.4 0.1 degpertilt
dose_induced_shrinkage -2.0 – 4.0 1.0 -
ctf_per_tilt_variation -0.15 – 0.15 0.0 um
missing_wedge 26.0 – 38.0 32.0 deg

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

16.13 dB

SSIM 0.1412

Scenario II (Mismatch)

15.22 dB

SSIM 0.0585

Scenario III (Oracle)

17.89 dB

SSIM 0.1644

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 15.51 0.1325 14.87 0.0590 18.06 0.1887
scene_01 16.91 0.1523 15.44 0.0596 17.59 0.1508
scene_02 16.78 0.1493 15.80 0.0608 18.12 0.1528
scene_03 15.33 0.1308 14.76 0.0544 17.78 0.1653

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffusionET + gradient 0.842 36.21 0.974 0.95 ✓ Certified Zhang et al., arXiv 2024
2 ETFormer + gradient 0.813 34.05 0.961 0.94 ✓ Certified Chen et al., CVPR 2024
3 DeePiCt + gradient 0.796 33.05 0.953 0.92 ✓ Certified Moebel et al., Nat. Methods 2021
4 CryoSeg + gradient 0.757 30.92 0.93 0.88 ✓ Certified Lamm et al., Nat. Methods 2022
5 DeepDeWedge + gradient 0.756 29.96 0.916 0.95 ✓ Certified Wiedemann et al., Nat. Methods 2024
6 IsoNet + gradient 0.722 28.32 0.887 0.92 ✓ Certified Liu et al., Nat. Commun. 2021
7 IMOD + gradient 0.625 23.5 0.75 0.95 ✓ Certified Kremer et al., J. Struct. Biol. 1996
8 SART-ET + gradient 0.561 21.61 0.673 0.88 ✓ Certified Andersen & Kak, Ultrason. Imaging 1984
9 WBP + gradient 0.451 17.62 0.481 0.91 ✓ Certified Crowther et al., Proc. R. Soc. 1970

Visible Data Fields

y H_ideal spec_ranges x_true true_spec

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 Cryo-Electron Tomography (Cryo-ET)