Hidden

Multispectral Satellite Imaging — Hidden Tier

(3 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
band_registration_error -0.14 – 0.46 px
atmospheric_transmittance 0.836 – 0.896 -
radiometric_calibration 0.993 – 1.023 -
pointing_jitter -0.07 – 0.23 px

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinIR + gradient 0.717 29.25 0.905 0.81 ✓ Certified Liang et al., ICCVW 2021
2 FlowCompute + gradient 0.706 28.54 0.892 0.82 ✓ Certified Huang et al., ECCV 2025
3 CompFormer + gradient 0.664 26.46 0.844 0.81 ✓ Certified Liu et al., ICCV 2024
4 Restormer + gradient 0.659 26.3 0.84 0.8 ✓ Certified Zamir et al., CVPR 2022
5 DiffusionCompute + gradient 0.636 25.59 0.82 0.76 ✓ Certified Zhang et al., NeurIPS 2024
6 NAFNet + gradient 0.627 25.09 0.805 0.77 ✓ Certified Chen et al., ICCV 2023
7 ART + gradient 0.627 25.01 0.803 0.78 ✓ Certified Gordon et al., J. Theor. Biol. 1970
8 LSQR + gradient 0.614 24.79 0.795 0.74 ✓ Certified Paige & Saunders, TOMS 1982
9 Deep Image Prior + gradient 0.595 23.5 0.75 0.8 ✓ Certified Ulyanov et al., CVPR 2018
10 PnP-RED + gradient 0.595 23.48 0.75 0.8 ✓ Certified Romano et al., IEEE TIP 2017
11 Tikhonov + gradient 0.590 23.46 0.749 0.78 ✓ Certified Tikhonov, Doklady Akad. Nauk SSSR 1963
12 PnP-ADMM + gradient 0.537 21.68 0.676 0.75 ✓ Certified Venkatakrishnan et al., 2013
13 Plug-and-Play + gradient 0.421 17.7 0.485 0.75 ✓ Certified Sreehari et al., IEEE TIP 2016

Dataset

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