E2GS: Event Enhanced Gaussian Splatting

TL;DR

E2GS is a novel method that integrates event data into Gaussian Splatting, enabling faster, high-quality view synthesis and deblurring for event cameras, with publicly available code.

Contribution

The paper introduces E2GS, combining event data with Gaussian Splatting to improve view synthesis and deblurring, reducing training and rendering times.

Findings

E2GS produces high-quality renderings on synthetic and real datasets.

E2GS achieves 140 FPS in rendering speed.

E2GS improves deblurring and view synthesis quality.

Abstract

Event cameras, known for their high dynamic range, absence of motion blur, and low energy usage, have recently found a wide range of applications thanks to these attributes. In the past few years, the field of event-based 3D reconstruction saw remarkable progress, with the Neural Radiance Field (NeRF) based approach demonstrating photorealistic view synthesis results. However, the volume rendering paradigm of NeRF necessitates extensive training and rendering times. In this paper, we introduce Event Enhanced Gaussian Splatting (E2GS), a novel method that incorporates event data into Gaussian Splatting, which has recently made significant advances in the field of novel view synthesis. Our E2GS effectively utilizes both blurry images and event data, significantly improving image deblurring and producing high-quality novel view synthesis. Our comprehensive experiments on both synthetic and real-world datasets demonstrate our E2GS can generate visually appealing renderings while offering faster training and rendering speed (140 FPS). Our code is available at https://github.com/deguchihiroyuki/E2GS.