AsyncEvGS: Asynchronous Event-Assisted Gaussian Splatting for Handheld Motion-Blurred Scenes

TL;DR

This paper presents AsyncEvGS, a novel asynchronous RGB-Event dual-camera system and reconstruction framework that enhances 3D scene reconstruction from motion-blurred images, outperforming existing methods.

Contribution

It introduces a high-resolution asynchronous RGB-Event system, a new reconstruction framework with robust pose estimation, and a high-res dataset for handheld motion-blurred scene reconstruction.

Findings

Achieves state-of-the-art results on challenging datasets.

Improves robustness of 3D reconstruction under severe motion blur.

Demonstrates effectiveness of asynchronous event data in 3D reconstruction.

Abstract

3D reconstruction methods such as 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) achieve impressive photorealism but fail when input images suffer from severe motion blur. While event cameras provide high-temporal-resolution motion cues, existing event-assisted approaches rely on low-resolution sensors and strict synchronization, limiting their practicality for handheld 3D capture on common devices, such as smartphones. We introduce a flexible, high-resolution asynchronous RGB-Event dual-camera system and a corresponding reconstruction framework. Our approach first reconstructs sharp images from the event data and then employs a cross-domain pose estimation module based on the Visual Geometry Transformer (VGGT) to obtain robust initialization for 3DGS. During optimization, we employ a structure-driven event loss and view-specific consistency regularizers to mitigate the ill-posed behavior of traditional event losses and deblurring losses, ensuring both stable and high-fidelity reconstruction. We further contribute AsyncEv-Deblur, a new high-resolution RGB-Event dataset captured with our asynchronous system. Experiments demonstrate that our method achieves state-of-the-art performance on both our challenging dataset and existing benchmarks, substantially improving reconstruction robustness under severe motion blur. Project page: https://openimaginglab.github.io/AsyncEvGS/