Public

Multispectral Satellite Imaging — 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
band_registration_error -0.2 – 0.4 0.1 px
atmospheric_transmittance 0.83 – 0.89 0.86 -
radiometric_calibration 0.99 – 1.02 1.005 -
pointing_jitter -0.1 – 0.2 0.05 px

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

9.15 dB

SSIM 0.0293

Scenario II (Mismatch)

9.19 dB

SSIM 0.0317

Scenario III (Oracle)

12.14 dB

SSIM 0.0697

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 9.16 0.0297 9.22 0.0309 12.17 0.0677
scene_01 9.15 0.0294 9.16 0.0324 12.11 0.0709
scene_02 9.12 0.0284 9.22 0.0318 12.17 0.0694
scene_03 9.15 0.0298 9.16 0.0316 12.11 0.0708

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 FlowCompute + gradient 0.846 36.73 0.977 0.94 ✓ Certified Huang et al., ECCV 2025
2 Restormer + gradient 0.820 34.64 0.965 0.94 ✓ Certified Zamir et al., CVPR 2022
3 DiffusionCompute + gradient 0.820 35.05 0.968 0.91 ✓ Certified Zhang et al., NeurIPS 2024
4 NAFNet + gradient 0.816 34.27 0.963 0.94 ✓ Certified Chen et al., ICCV 2023
5 CompFormer + gradient 0.811 34.85 0.967 0.88 ✓ Certified Liu et al., ICCV 2024
6 SwinIR + gradient 0.809 34.06 0.961 0.92 ✓ Certified Liang et al., ICCVW 2021
7 Deep Image Prior + gradient 0.764 31.27 0.934 0.89 ✓ Certified Ulyanov et al., CVPR 2018
8 PnP-ADMM + gradient 0.717 28.24 0.886 0.9 ✓ Certified Venkatakrishnan et al., 2013
9 PnP-RED + gradient 0.705 27.6 0.872 0.9 ✓ Certified Romano et al., IEEE TIP 2017
10 Plug-and-Play + gradient 0.691 27.27 0.865 0.86 ✓ Certified Sreehari et al., IEEE TIP 2016
11 LSQR + gradient 0.685 26.18 0.837 0.94 ✓ Certified Paige & Saunders, TOMS 1982
12 ART + gradient 0.671 26.21 0.838 0.87 ✓ Certified Gordon et al., J. Theor. Biol. 1970
13 Tikhonov + gradient 0.622 23.79 0.761 0.9 ✓ Certified Tikhonov, Doklady Akad. Nauk SSSR 1963

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 Multispectral Satellite Imaging