Public

Image Scanning Microscopy (ISM) — 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
detector_element_offset -0.2 – 0.4 0.1 px
magnification_error -1.0 – 2.0 0.5 relative

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

13.27 dB

SSIM 0.3991

Scenario II (Mismatch)

11.88 dB

SSIM 0.2385

Scenario III (Oracle)

19.75 dB

SSIM 0.4579

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 17.02 0.3838 14.94 0.2440 20.04 0.5013
scene_01 14.23 0.2969 12.92 0.2098 19.23 0.5480
scene_02 8.52 0.3871 8.01 0.2308 20.11 0.3417
scene_03 13.30 0.5284 11.66 0.2694 19.61 0.4408

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 Restormer+ + gradient 0.839 36.16 0.974 0.94 ✓ Certified Zamir et al., ICCV 2024
2 ScoreMicro + gradient 0.828 36.24 0.975 0.88 ✓ Certified Wei et al., ECCV 2025
3 DiffDeconv + gradient 0.824 35.55 0.971 0.9 ✓ Certified Huang et al., NeurIPS 2024
4 ResUNet + gradient 0.817 34.67 0.966 0.92 ✓ Certified DeCelle et al., Nat. Methods 2021
5 DeconvFormer + gradient 0.814 35.28 0.969 0.87 ✓ Certified Chen et al., CVPR 2024
6 CARE + gradient 0.798 32.96 0.952 0.94 ✓ Certified Weigert et al., Nat. Methods 2018
7 Restormer + gradient 0.795 33.72 0.959 0.87 ✓ Certified Zamir et al., CVPR 2022
8 U-Net + gradient 0.783 32.41 0.947 0.9 ✓ Certified Ronneberger et al., MICCAI 2015
9 PnP-DnCNN + gradient 0.750 29.84 0.914 0.93 ✓ Certified Zhang et al., IEEE TIP 2017
10 PnP-FISTA + gradient 0.707 27.74 0.875 0.9 ✓ Certified Bai et al., 2020
11 TV-Deconvolution + gradient 0.690 26.71 0.851 0.91 ✓ Certified Rudin et al., Phys. A 1992
12 Wiener Filter + gradient 0.662 25.4 0.815 0.91 ✓ Certified Analytical baseline
13 Richardson-Lucy + gradient 0.637 24.4 0.782 0.9 ✓ Certified Richardson, JOSA 1972 / Lucy, AJ 1974

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 Image Scanning Microscopy (ISM)