GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation
This provides a high-fidelity synthetic event dataset for event vision research, addressing limitations in existing datasets, though it is incremental as it builds on existing simulation and reconstruction methods.
The paper tackles the lack of diverse and geometrically consistent synthetic event datasets by introducing GS2E, a large-scale dataset generated from real-world sparse multi-view RGB images using 3D Gaussian Splatting and a novel event simulation pipeline, which demonstrates superior generalization in event-based 3D reconstruction tasks.
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.