Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion

Tianyi Xiong, Jiayi Wu, Botao He, Cornelia Fermuller, Yiannis Aloimonos, Heng Huang, Christopher Metzler

Keywords: Event-based 3D Reconstruction, Gaussian Splatting, High-speed Robot Egomotion

Abstract:

By combining differentiable rendering with explicit point-based scene representations, 3D Gaussian Splatting (3DGS) has demonstrated breakthrough 3D reconstruction capabilities.
However, to date 3DGS has had limited impact on robotics, where high-speed egomotion is pervasive: Egomotion introduces motion blur and leads to artifacts in existing frame-based 3DGS reconstruction methods.
To address this challenge, we introduce Event3DGS, an event-based 3DGS framework.
By exploiting the exceptional temporal resolution of event cameras, Event3GDS can reconstruct high-fidelity 3D structure and appearance under high-speed egomotion.
Extensive experiments on multiple synthetic and real-world datasets demonstrate the superiority of Event3DGS compared with existing event-based dense 3D scene reconstruction frameworks; Event3DGS substantially improves reconstruction quality (+3dB) while reducing computational costs by 95\%.
Our framework also allows one to incorporate a few motion-blurred frame-based measurements into the reconstruction process to further improve appearance fidelity without loss of structural accuracy.

Video: https://youtu.be/QXbrx1n6h5g

Website: https://tyxiong23.github.io/event3dgs

Student Paper: yes

Submission Number: 126