SweepEvGS: Event-Based 3D Gaussian Splatting for Macro and Micro Radiance Field Rendering from a Single Sweep

TL;DR

SweepEvGS introduces a novel event-camera-based method for high-quality, fast, and efficient 3D scene reconstruction and view synthesis from a single sweep, overcoming limitations of traditional dense image capture.

Contribution

It leverages event cameras and a single sweep to enable robust 3D Gaussian splatting for dynamic scene rendering, a significant advancement over existing methods requiring dense images.

Findings

Outperforms existing methods in visual quality and speed.

Effective in synthetic, macro, and micro real-world environments.

Demonstrates robustness and efficiency in diverse imaging settings.

Abstract

Recent advancements in 3D Gaussian Splatting (3D-GS) have demonstrated the potential of using 3D Gaussian primitives for high-speed, high-fidelity, and cost-efficient novel view synthesis from continuously calibrated input views. However, conventional methods require high-frame-rate dense and high-quality sharp images, which are time-consuming and inefficient to capture, especially in dynamic environments. Event cameras, with their high temporal resolution and ability to capture asynchronous brightness changes, offer a promising alternative for more reliable scene reconstruction without motion blur. In this paper, we propose SweepEvGS, a novel hardware-integrated method that leverages event cameras for robust and accurate novel view synthesis across various imaging settings from a single sweep. SweepEvGS utilizes the initial static frame with dense event streams captured during a single camera sweep to effectively reconstruct detailed scene views. We also introduce different real-world hardware imaging systems for real-world data collection and evaluation for future research. We validate the robustness and efficiency of SweepEvGS through experiments in three different imaging settings: synthetic objects, real-world macro-level, and real-world micro-level view synthesis. Our results demonstrate that SweepEvGS surpasses existing methods in visual rendering quality, rendering speed, and computational efficiency, highlighting its potential for dynamic practical applications.