CVJun 5, 2024

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

arXiv:2406.02972v431 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of high-fidelity 3D scene reconstruction for robotics applications where high-speed motion is common, representing a domain-specific advancement.

The paper tackled the problem of 3D reconstruction under high-speed robot egomotion, which causes motion blur and artifacts in existing methods, by introducing Event3DGS, an event-based 3D Gaussian Splatting framework that improves reconstruction quality by +3dB and reduces computational costs by 95%.

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 {\em 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes