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

Li Yuan (Peking University) · Yonghong Tian (School of Computer Science, Peking University) · Yuchen Li (Peking University) · Chaoran Feng (Peking University) · Zhenyu Tang (Peking University) · Kaiyuan Deng (University of Arizona) · Wangbo Yu (Peking University)

adaptive trajectory interpolationevent contrast threshold modelingevent simulation pipelineevent-based 3d reconstructiongaussian splattinggeometric inconsistencygeometrically consistent event streamsgs2ehigh-fidelity event visionmotion and lighting conditionsmulti-view rgb imagesphotorealistic static scenessynthetic event datasettemporally dense event streamsviewpoint diversity

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.