Ev-GS: Event-based Gaussian splatting for Efficient and Accurate Radiance Field Rendering

TL;DR

Ev-GS introduces a novel event-based Gaussian splatting method for efficient and accurate 3D radiance field rendering from monocular event camera data, outperforming existing neural radiance field approaches in speed and quality.

Contribution

It is the first CNI-informed scheme to infer 3D Gaussian splatting from event camera data, enabling fast, high-quality novel view synthesis with reduced computational costs.

Findings

Outperforms frame-based input methods in visual quality

Achieves competitive reconstruction quality with less computation

Enables efficient rendering of fast-moving objects in challenging lighting

Abstract

Computational neuromorphic imaging (CNI) with event cameras offers advantages such as minimal motion blur and enhanced dynamic range, compared to conventional frame-based methods. Existing event-based radiance field rendering methods are built on neural radiance field, which is computationally heavy and slow in reconstruction speed. Motivated by the two aspects, we introduce Ev-GS, the first CNI-informed scheme to infer 3D Gaussian splatting from a monocular event camera, enabling efficient novel view synthesis. Leveraging 3D Gaussians with pure event-based supervision, Ev-GS overcomes challenges such as the detection of fast-moving objects and insufficient lighting. Experimental results show that Ev-GS outperforms the method that takes frame-based signals as input by rendering realistic views with reduced blurring and improved visual quality. Moreover, it demonstrates competitive reconstruction quality and reduced computing occupancy compared to existing methods, which paves the way to a highly efficient CNI approach for signal processing.