Dev

Event Camera / Dynamic Vision Sensor (DVS) — Dev Tier

(5 scenes)

Blind evaluation tier — no ground truth available.

What you get

Measurements (y), ideal forward operator (H), and spec ranges only.

How to use

Apply your pipeline from the Public tier. Use consistency as self-check.

What to submit

Reconstructed signals and corrected spec. Scored server-side.

Parameter Specifications

🔒

True spec hidden — estimate parameters from spec ranges below.

Parameter Spec Range Unit
contrast_threshold 0.252 – 0.372 logintensity
refractory_period -1.16 – 4.24 us
noise_event_rate -0.24 – 0.36 ofrealevents
hot_pixel_fraction -0.12 – 0.18 -

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffEvent + gradient 0.776 33.47 0.957 0.79 ✓ Certified Gao et al., NeurIPS 2024
2 SwinEvent + gradient 0.761 31.6 0.938 0.85 ✓ Certified Zhang et al., CVPR 2023
3 PhysEvent + gradient 0.735 29.37 0.907 0.89 ✓ Certified Chen et al., ECCV 2024
4 TransEvent + gradient 0.714 29.0 0.9 0.82 ✓ Certified Weng et al., ECCV 2022
5 Complementary + gradient 0.596 23.23 0.74 0.84 ✓ Certified Scheerlinck et al., RA-L 2018
6 SPADE-E2VID + gradient 0.581 22.78 0.722 0.82 ✓ Certified Cadena et al., IEEE TIP 2021
7 FireNet + gradient 0.517 20.25 0.611 0.85 ✓ Certified Scheerlinck et al., WACV 2020
8 Event-Integration + gradient 0.517 20.26 0.611 0.85 ✓ Certified Mead & Mahowald, Analog VLSI 1989
9 E2VID + gradient 0.481 18.97 0.548 0.86 ✓ Certified Rebecq et al., IEEE TPAMI 2020

Visible Data Fields

y H_ideal spec_ranges

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)