EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images

TL;DR

EvaGaussians introduces a novel method that uses event camera data to improve 3D scene reconstruction and view synthesis from blurry images, overcoming limitations of traditional approaches that require sharp images and accurate poses.

Contribution

The paper presents a new approach integrating event streams with Gaussian Splatting to effectively reconstruct 3D scenes from blurry images, jointly optimizing scene parameters and camera motion.

Findings

Outperforms state-of-the-art deblurring methods in detail restoration.

Produces high-fidelity novel views from motion-blurred images.

Effectively models motion blur using event camera data.

Abstract

3D Gaussian Splatting (3D-GS) has demonstrated exceptional capabilities in 3D scene reconstruction and novel view synthesis. However, its training heavily depends on high-quality, sharp images and accurate camera poses. Fulfilling these requirements can be challenging in non-ideal real-world scenarios, where motion-blurred images are commonly encountered in high-speed moving cameras or low-light environments that require long exposure times. To address these challenges, we introduce Event Stream Assisted Gaussian Splatting (EvaGaussians), a novel approach that integrates event streams captured by an event camera to assist in reconstructing high-quality 3D-GS from blurry images. Capitalizing on the high temporal resolution and dynamic range offered by the event camera, we leverage the event streams to explicitly model the formation process of motion-blurred images and guide the deblurring reconstruction of 3D-GS. By jointly optimizing the 3D-GS parameters and recovering camera motion trajectories during the exposure time, our method can robustly facilitate the acquisition of high-fidelity novel views with intricate texture details. We comprehensively evaluated our method and compared it with previous state-of-the-art deblurring rendering methods. Both qualitative and quantitative comparisons demonstrate that our method surpasses existing techniques in restoring fine details from blurry images and producing high-fidelity novel views.