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

Yuchen Li, Chaoran Feng, Zhenyu Tang, Kaiyuan Deng, Wangbo Yu, Yonghong Tian, Li Yuan

Keywords: Event Cameras; Large-scale 3D Reconstruction Dataset; Novel View Synthesis; Deblurring

TL;DR: We present 3D Gaussian Splatting to Event Generation (GS2E), a large-scale event synthetic dataset designed for high-fidelity event vision tasks from real-world sparse multi-view RGB images.

Abstract: We introduce GS2E (Gaussian Splatting to Event Generation), a large-scale synthetic event dataset designed 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 suffer from limited viewpoint diversity and geometric inconsistency, or rely on expensive, hard-to-scale hardware setups. GS2E addresses these limitations by first reconstructing photorealistic static scenes using 3D Gaussian Splatting, followed by a novel, physically-informed event simulation pipeline. This pipeline integrates adaptive trajectory interpolation with physically-consistent event contrast threshold modeling. As a result, it generates temporally dense and geometrically consistent event streams under diverse motion and lighting conditions, while maintaining strong alignment with the underlying scene structure. Experimental results on event-based 3D reconstruction highlight GS2E’s superior generalization capabilities and its practical value as a benchmark for advancing event vision research.

Dataset URL: https://huggingface.co/datasets/INTOTHEMILD/GS2E

Code URL: https://github.com/PKU-YuanGroup/GS2E

Primary Area: Datasets & Benchmarks for applications in computer vision

Submission Number: 18