EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Wangbo, Feng, Chaoran, Tang, Jiye, Yang, Jiashu, Tang, Zhenyu, Jia, Xu, Yang, Yuchao, Yuan, Li, Tian, Yonghong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910730298589184
author Yu, Wangbo
Feng, Chaoran
Tang, Jiye
Yang, Jiashu
Tang, Zhenyu
Jia, Xu
Yang, Yuchao
Yuan, Li
Tian, Yonghong
author_facet Yu, Wangbo
Feng, Chaoran
Tang, Jiye
Yang, Jiashu
Tang, Zhenyu
Jia, Xu
Yang, Yuchao
Yuan, Li
Tian, Yonghong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20224
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images
Yu, Wangbo
Feng, Chaoran
Tang, Jiye
Yang, Jiashu
Tang, Zhenyu
Jia, Xu
Yang, Yuchao
Yuan, Li
Tian, Yonghong
Computer Vision and Pattern Recognition
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.
title EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.20224