EvFlow-GS: Event Enhanced Motion Deblurring with Optical Flow for 3D Gaussian Splatting

TL;DR

EvFlow-GS introduces a unified framework combining event streams and optical flow to enhance 3D reconstruction from motion-blurred images, reducing artifacts and improving detail accuracy.

Contribution

It proposes a novel end-to-end learnable double integral method and a joint optimization of 3D Gaussian Splatting with event-based supervision.

Findings

Outperforms existing methods in 3D reconstruction quality.

Effectively reduces residual artifacts and blurry textures.

Demonstrates superior performance on benchmark datasets.

Abstract

Achieving sharp 3D reconstruction from motion-blurred images alone becomes challenging, motivating recent methods to incorporate event cameras, benefiting from microsecond temporal resolution. However, they suffer from residual artifacts and blurry texture details due to misleading supervision from inaccurate event double integral priors and noisy, blurry events. In this study, we propose EvFlow-GS, a unified framework that leverages event streams and optical flow to optimize an end-to-end learnable double integral (LDI), camera poses, and 3D Gaussian Splatting (3DGS) jointly on-the-fly. Specifically, we first extract edge information from the events using optical flow and then formulate a novel event-based loss applied separately to different modules. Additionally, we exploit a novel event-residual prior to strengthen the supervision of intensity changes between images rendered from 3DGS. Finally, we integrate the outputs of both 3DGS and LDI into a joint loss, enabling their optimization to mutually facilitate each other. Experiments demonstrate the leading performance of our EvFlow-GS.