E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations

TL;DR

This paper introduces E2V-SDE, a neural stochastic differential equation-based model that reconstructs high-quality, continuous videos from asynchronous event camera data with improved speed and temporal consistency.

Contribution

The paper proposes a novel SDE-based framework for event-to-video reconstruction, enhancing quality, speed, and temporal continuity over existing methods.

Findings

Outperforms state-of-the-art in video quality and speed

LPIPS score improves by up to 12%

Reconstruction speed is 87% faster than ET-Net

Abstract

Event cameras respond to brightness changes in the scene asynchronously and independently for every pixel. Due to the properties, these cameras have distinct features: high dynamic range (HDR), high temporal resolution, and low power consumption. However, the results of event cameras should be processed into an alternative representation for computer vision tasks. Also, they are usually noisy and cause poor performance in areas with few events. In recent years, numerous researchers have attempted to reconstruct videos from events. However, they do not provide good quality videos due to a lack of temporal information from irregular and discontinuous data. To overcome these difficulties, we introduce an E2V-SDE whose dynamics are governed in a latent space by Stochastic differential equations (SDE). Therefore, E2V-SDE can rapidly reconstruct images at arbitrary time steps and make realistic predictions on unseen data. In addition, we successfully adopted a variety of image composition techniques for improving image clarity and temporal consistency. By conducting extensive experiments on simulated and real-scene datasets, we verify that our model outperforms state-of-the-art approaches under various video reconstruction settings. In terms of image quality, the LPIPS score improves by up to 12% and the reconstruction speed is 87% higher than that of ET-Net.