Public

Streak Camera 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
sweep_nonlinearity -1.0 – 2.0 0.5 -
temporal_resolution 0.2 – 2.6 1.4 ps
dynamic_range_saturation -2.0 – 4.0 1.0 -
trigger_jitter -2.0 – 4.0 1.0 ps

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 UltraFormer + gradient 0.781 32.71 0.95 0.87 ✓ Certified Ultrafast transformer, 2024
2 AL-DL + gradient 0.763 31.59 0.938 0.86 ✓ Certified Yao et al., Photon. Res. 2021
3 Temporal-U-Net + gradient 0.754 30.56 0.925 0.89 ✓ Certified 3D/Temporal U-Net variant
4 CUP-Net + gradient 0.739 29.77 0.913 0.88 ✓ Certified Parker et al., 2021
5 Unfolded-CUP + gradient 0.727 28.47 0.89 0.93 ✓ Certified CUP algorithm unfolding
6 DiffusionUltrafast + gradient 0.709 28.15 0.884 0.87 ✓ Certified Zhang et al., 2024
7 ScoreUltrafast + gradient 0.688 26.75 0.852 0.9 ✓ Certified Wei et al., 2025
8 PnP-FFDNet + gradient 0.670 26.05 0.833 0.88 ✓ Certified Yuan et al., 2020
9 Temporal Filtering + gradient 0.667 25.36 0.813 0.94 ✓ Certified Analytical baseline
10 PnP-ADMM + gradient 0.637 24.48 0.785 0.89 ✓ Certified ADMM + denoiser prior
11 TwIST + gradient 0.614 23.21 0.739 0.93 ✓ Certified Bioucas-Dias & Figueiredo, IEEE TIP 2007

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 Streak Camera Imaging