Public

High Dynamic Range (HDR) Imaging — 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
camera_response_function_error -2.0 – 4.0 1.0 -
exposure_ratio_error -2.0 – 4.0 1.0 -
ghost_artifact_(motion_between_exposures) -1.0 – 2.0 0.5 px

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

7.84 dB

SSIM 0.3015

Scenario II (Mismatch)

7.84 dB

SSIM 0.1991

Scenario III (Oracle)

10.94 dB

SSIM 0.3682

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 7.64 0.2894 7.66 0.2019 10.79 0.3739
scene_01 7.65 0.3040 7.65 0.1960 10.77 0.3632
scene_02 8.07 0.3073 8.08 0.2002 11.17 0.3690
scene_03 8.02 0.3052 7.95 0.1985 11.04 0.3666

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffusionPhoto + gradient 0.853 37.47 0.98 0.93 ✓ Certified Zhang et al., NeurIPS 2024
2 HDRFormer + gradient 0.822 35.22 0.969 0.91 ✓ Certified Eilertsen et al., ICCV 2024
3 Uformer + gradient 0.822 34.95 0.967 0.93 ✓ Certified Wang et al., CVPR 2022
4 DeblurGaussian + gradient 0.818 35.1 0.968 0.9 ✓ Certified Liang et al., CVPR 2024
5 U-Net + gradient 0.809 34.03 0.961 0.92 ✓ Certified Ronneberger et al., MICCAI 2015
6 HDR-CNN + gradient 0.804 33.38 0.956 0.94 ✓ Certified Eilertsen et al., ACM TOG 2017
7 PhotoFormer + gradient 0.802 33.67 0.958 0.91 ✓ Certified Zhang et al., ICCV 2024
8 ScorePhoto + gradient 0.792 33.34 0.956 0.88 ✓ Certified Wei et al., ECCV 2025
9 LaplacianFormer + gradient 0.755 30.49 0.924 0.9 ✓ Certified Chen et al., CVPR 2022
10 PnP-ADMM + gradient 0.732 29.0 0.9 0.91 ✓ Certified Venkatakrishnan et al., 2013
11 PnP-FFDNet + gradient 0.728 28.86 0.898 0.9 ✓ Certified Zhang et al., 2017
12 Wiener-Deconv + gradient 0.691 26.7 0.851 0.92 ✓ Certified Analytical baseline
13 Lucy-Richardson + gradient 0.631 24.33 0.78 0.88 ✓ Certified Lucy, AJ 1974
14 Laplacian Pyramid + gradient 0.624 23.94 0.766 0.89 ✓ Certified Burt & Adelson, TPAMI 1983

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 High Dynamic Range (HDR) Imaging