Public

Event Camera / Dynamic Vision Sensor (DVS) — 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
contrast_threshold 0.26 – 0.38 0.32 logintensity
refractory_period -0.8 – 4.6 1.9 us
noise_event_rate -0.2 – 0.4 0.1 ofrealevents
hot_pixel_fraction -0.1 – 0.2 0.05 -

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 DiffEvent + gradient 0.838 36.4 0.975 0.92 ✓ Certified Gao et al., NeurIPS 2024
2 PhysEvent + gradient 0.823 35.93 0.973 0.87 ✓ Certified Chen et al., ECCV 2024
3 SwinEvent + gradient 0.808 34.11 0.962 0.91 ✓ Certified Zhang et al., CVPR 2023
4 TransEvent + gradient 0.785 32.73 0.95 0.89 ✓ Certified Weng et al., ECCV 2022
5 SPADE-E2VID + gradient 0.749 30.14 0.919 0.9 ✓ Certified Cadena et al., IEEE TIP 2021
6 FireNet + gradient 0.709 27.94 0.88 0.89 ✓ Certified Scheerlinck et al., WACV 2020
7 E2VID + gradient 0.664 25.78 0.826 0.88 ✓ Certified Rebecq et al., IEEE TPAMI 2020
8 Complementary + gradient 0.614 23.06 0.733 0.95 ✓ Certified Scheerlinck et al., RA-L 2018
9 Event-Integration + gradient 0.502 19.4 0.57 0.9 ✓ Certified Mead & Mahowald, Analog VLSI 1989

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 Event Camera / Dynamic Vision Sensor (DVS)