HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks

TL;DR

HyperE2VID introduces a hypernetwork-based neural architecture that enhances event-based video reconstruction by adaptively filtering event data, leading to superior quality and efficiency over existing methods.

Contribution

This paper presents HyperE2VID, a novel hypernetwork approach with adaptive filters and curriculum learning for improved event-based video reconstruction.

Findings

Outperforms state-of-the-art in reconstruction quality

Uses fewer parameters and computational resources

Achieves faster inference times

Abstract

Event-based cameras are becoming increasingly popular for their ability to capture high-speed motion with low latency and high dynamic range. However, generating videos from events remains challenging due to the highly sparse and varying nature of event data. To address this, in this study, we propose HyperE2VID, a dynamic neural network architecture for event-based video reconstruction. Our approach uses hypernetworks to generate per-pixel adaptive filters guided by a context fusion module that combines information from event voxel grids and previously reconstructed intensity images. We also employ a curriculum learning strategy to train the network more robustly. Our comprehensive experimental evaluations across various benchmark datasets reveal that HyperE2VID not only surpasses current state-of-the-art methods in terms of reconstruction quality but also achieves this with fewer parameters, reduced computational requirements, and accelerated inference times.