GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation

TL;DR

GS2E introduces a large-scale, photorealistic synthetic event dataset generated from 3D Gaussian Splatting and a novel event simulation pipeline, addressing limitations of existing datasets and enhancing event vision research.

Contribution

The paper presents GS2E, a new synthetic event dataset created using 3D Gaussian Splatting and a physically-informed simulation pipeline, improving diversity and realism over prior datasets.

Findings

GS2E outperforms existing datasets in event-based 3D reconstruction tasks.

The dataset demonstrates strong generalization capabilities across diverse conditions.

GS2E provides a valuable benchmark for advancing event vision research.

Abstract

We introduce GS2E (Gaussian Splatting to Event), a large-scale synthetic event dataset for high-fidelity event vision tasks, captured from real-world sparse multi-view RGB images. Existing event datasets are often synthesized from dense RGB videos, which typically lack viewpoint diversity and geometric consistency, or depend on expensive, difficult-to-scale hardware setups. GS2E overcomes these limitations by first reconstructing photorealistic static scenes using 3D Gaussian Splatting, and subsequently employing a novel, physically-informed event simulation pipeline. This pipeline generally integrates adaptive trajectory interpolation with physically-consistent event contrast threshold modeling. Such an approach yields temporally dense and geometrically consistent event streams under diverse motion and lighting conditions, while ensuring strong alignment with underlying scene structures. Experimental results on event-based 3D reconstruction demonstrate GS2E's superior generalization capabilities and its practical value as a benchmark for advancing event vision research.