Public

SIM — Public Tier

(5 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
pattern_phase -0.05 – 0.1 0.025 rad
pattern_freq -1.0 – 2.0 0.5 %
modulation_depth -5.0 – 10.0 2.5 %

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

23.08 dB

SSIM 0.3869

Scenario II (Mismatch)

22.00 dB

SSIM 0.2417

Scenario III (Oracle)

7.05 dB

SSIM 0.0036

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 21.66 0.1890 21.17 0.0819 8.45 0.0044
scene_01 23.64 0.5875 20.70 0.3142 8.77 0.0044
scene_02 24.77 0.5136 24.52 0.4213 5.36 0.0030
scene_03 22.25 0.2575 21.62 0.1495 5.60 0.0027

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SIMformer + gradient 0.805 34.37 0.964 0.88 ✓ Certified SIM reconstruction transformer, 2024
2 DL-SIM + gradient 0.785 33.01 0.953 0.87 ✓ Certified Jin et al., Nat. Methods 2023
3 PnP-SIM + gradient 0.731 29.3 0.906 0.88 ✓ Certified PnP with SIM forward model
4 Wiener-SIM + gradient 0.698 26.85 0.854 0.94 ✓ Certified Gustafsson, J. Microsc. 2000

Visible Data Fields

y H_ideal spec_ranges x_true true_spec

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%
Back to SIM