event-camera

NYC-Event-VPR

ES-PTAM

Official implementation of ECCVW 2024 paper "ES-PTAM: Event-based Stereo Parallel Tracking and Mapping"

ddd20-utils

DDD20 End-to-End Event Camera Driving Dataset

EventEgo3D

EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams [CVPR'24]

event_based_bos

Event-based Background-Oriented Schlieren (IEEE TPAMI 2023)

event-vision-library

A library for event-based vision

EventHDR

This is the implementation and dataset for Learning To Reconstruct High Speed and High Dynamic Range Videos From Events, CVPR 2021, and EventHDR: From Event to High-Speed HDR Videos and Beyond, TPAMI 2024

Deblurring-Low-Light-Images-with-Events

IJCV2023 paper: Deblurring Low-Light Images with Events

event-based-monocular-hpe

Code for "Lifting Monocular Events to 3D Human Poses" - CVPRw 2021

EAS-SNN

Code for "End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks", ECCV 2024

SSTFormer

[PokerEvent Benchmark Dataset & SNN-ANN Baseline] Official PyTorch implementation of "SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition"

CeleX-HAR

Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms

MVSEC-NIGHTL21

A labeled dataset from a subset of the MVSEC dataset for car detection at night driving conditions.

event-based-velocity-prediction-snn

Neuromorphic computing uses very-large-scale integration (VLSI) systems with the goal of replicating neurobiological structures and signal conductance mechanisms. Neuromorphic processors can run spiking neural networks (SNNs) that mimic how biological neurons function, particularly by emulating the emission of electrical spikes. A key benefit of using SNNs and neuromorphic technology is the ability to optimize the size, weight, and power consumed in a system. SNNs can be trained and employed in various robotic and computer vision applications; we attempt to use event-based to create a novel approach in order to the predict velocity of objects moving in frame. Data generated in this work is recorded and simulated as event camera data using ESIM. Vicon motion tracking data provides the ground truth position and time values, from which the velocity is calculated. The SNNs developed in this work regress the velocity vector, consisting of the x, y, and z-components, while using the event data, or the list of events associated with each velocity measurement, as the input features. With the use of the novel dataset created, three SNN models were trained and then the model that minimized the loss function the most was further validated by omitting a subset of data used in the original training. The average loss, in terms of RMSE, on the test set after using the trained model on the omitted subset of data was 0.000386. Through this work, it is shown that it is possible to train an SNN on event data in order to predict the velocity of an object in view. (Spring 2022 MS Computer Science Thesis - North Carolina State University)

E-3DGS

Pytorch implementation of the paper 'E-3DGS: Gaussian Splatting with Exposure and Motion Events'

DSEC

Paper Reproduction for "Learning Monocular Dense Depth from Events" | CS4245 Computer Vision by Deep Learning course project

ALED

Code for the "Learning to Estimate Two Dense Depths from LiDAR and Event Data" article

Event-Intensity-Stereo

Implentation of Intensity+Event Stereo Matching described in 'Self-Supervised Intensity-Event Stereo Matching'''

event_batch

Event batch estimation from adaptive global decay process

Sim2E

Mujoco based Robotic arm simulator with an Esim-based neuromorphic vision sensor simulator, rendered in Unity3D

event-based-odomety

Fully Event-Inspired Visual Odometry, consisting of 1) Event-based Feature Tracker; 2) Monocular Visual Odometry based on feature tracks; 3) Motion Compensation of event images.

CoCapture

GUI for viewing and recording with multi camera systems including event cameras.

ev_deep_motion_segmentation

Motion Segmentation for Neuromorphic Aerial Surveillance

SLED

Code for generating the SLED dataset, as described in the "Learning to Estimate Two Dense Depths from LiDAR and Event Data" article

OpenESL

Event based Sign-Language-Translation

ECRot

An event camera dataset for rotational motion related study. See T-RO 2024 paper CMax-SLAM

Event_Camera_3D_Stereo_Project

3D reconstruction based on stereo event-camera data, 2020SoSe, TU Berlin

dv-ros2

ROS2 wrapper for iniVation event cameras using dv-processing.

Background-Activity-Denoising-for-Event-Camera

An individual project related to denoising for event camera

ETTCM

Time-to-contact map by joint estimation of up-to-scale inverse depth and global motion using a single event camera

LETGAN

How to Learn a Domain Adaptive Event Simulator? ACM MM, 2021

event_camera_emulation

Emulation of event camera data using standard RGB images

Stereo-Event-Based-Reconstruction-with-Active-Laser-Features

Reconstructing a depth map by from two DAVIS and a controlled laser.

EEPPR

Event-based Estimation of Periodic Phenomena Rate using Correlation in 3D - Kolář, J., Špetlík, R., Matas, J. (2024), In Proceedings of the 17th International Conference on Machine Vision (ICMV 2024)

evshow

Framerize event data and visualize it as images.