SOTAVerified

Event-based vision

An event camera, also known as a neuromorphic camera, silicon retina or dynamic vision sensor, is an imaging sensor that responds to local changes in brightness. Event cameras do not capture images using a shutter as conventional cameras do. Instead, each pixel inside an event camera operates independently and asynchronously, reporting changes in brightness as they occur and staying silent otherwise. Modern event cameras have microsecond temporal resolution, 120 dB dynamic range, and less under/overexposure and motion blur than frame cameras.

Title	Date	Tasks	Status
Covariant spatio-temporal receptive fields for spiking neural networks	May 1, 2024	Event-based vision	CodeCode Available
Event-Based Crossing Dataset (EBCD)	Mar 21, 2025	Event-based visionobject-detection	CodeCode Available
Event-based Camera Pose Tracking using a Generative Event Model	Oct 7, 2015	Camera LocalizationEvent-based vision	CodeCode Available
On the Generation of a Synthetic Event-Based Vision Dataset for Navigation and Landing	Aug 1, 2023	Event-based visionScene Generation	CodeCode Available
A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks	Jul 2, 2019	Event-based vision	CodeCode Available

Title

Status

Hype

Covariant spatio-temporal receptive fields for spiking neural networks

CodeCode Available

Event-Based Crossing Dataset (EBCD)

CodeCode Available

Event-based Camera Pose Tracking using a Generative Event Model

CodeCode Available

On the Generation of a Synthetic Event-Based Vision Dataset for Navigation and Landing

CodeCode Available

A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks

CodeCode Available

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	RED	mAP	43	—	Unverified

Event-based vision

Papers

Benchmark Results