Event-based vision

15 papers with code • 1 benchmarks • 4 datasets

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.

Most implemented papers

Event-based Vision: A Survey

uzh-rpg/event-based_vision_resources 17 Apr 2019

Event cameras offer attractive properties compared to traditional cameras: high temporal resolution (in the order of microseconds), very high dynamic range (140 dB vs. 60 dB), low power consumption, and high pixel bandwidth (on the order of kHz) resulting in reduced motion blur.

Event-based Camera Pose Tracking using a Generative Event Model

uzh-rpg/rpg_image_reconstruction_from_events 7 Oct 2015

Event-based vision sensors mimic the operation of biological retina and they represent a major paradigm shift from traditional cameras.

Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception

tudelft/cuSNN 28 Jul 2018

Convolutional layers with input synapses characterized by single and multiple transmission delays are employed for feature and local motion perception, respectively; while global motion selectivity emerges in a final fully-connected layer.

Focus Is All You Need: Loss Functions For Event-based Vision

tub-rip/dvs_global_flow_skeleton CVPR 2019

The proposed loss functions allow bringing mature computer vision tools to the realm of event cameras.

Event Cameras, Contrast Maximization and Reward Functions: An Analysis

TimoStoff/events_contrast_maximization CVPR 2019

The versatility of this approach has lead to a flurry of research in recent years, but no in-depth study of the reward chosen during optimization has yet been made.

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

deepspike/tandem_learning 2 Jul 2019

Spiking neural networks (SNNs) represent the most prominent biologically inspired computing model for neuromorphic computing (NC) architectures.

A Large Scale Event-based Detection Dataset for Automotive

prophesee-ai/prophesee-automotive-dataset-toolbox 23 Jan 2020

We introduce the first very large detection dataset for event cameras.

Lifting Monocular Events to 3D Human Poses

IIT-PAVIS/lifting_events_to_3d_hpe 21 Apr 2021

Here we propose the first learning-based method for 3D human pose from a single stream of events.

Bridging the Gap between Events and Frames through Unsupervised Domain Adaptation

uzh-rpg/rpg_ev-transfer 6 Sep 2021

However, event-based vision has been held back by the shortage of labeled datasets due to the novelty of event cameras.

Moving Object Detection for Event-based vision using Graph Spectral Clustering

anindya2001/GSCEventMOD International Conference on Computer Vision Workshops 2021

However, these advantages come at a high cost, as the event camera data typically contains more noise and has low resolution.