DeblurSplat: SfM-free 3D Gaussian Splatting with Event Camera for Robust Deblurring

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Pengteng, Lu, Yunfan, Song, Pinhao, Guo, Weiyu, Yao, Huizai, Yu, F. Richard, Xiong, Hui
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916062623170560
author Li, Pengteng
Lu, Yunfan
Song, Pinhao
Guo, Weiyu
Yao, Huizai
Yu, F. Richard
Xiong, Hui
author_facet Li, Pengteng
Lu, Yunfan
Song, Pinhao
Guo, Weiyu
Yao, Huizai
Yu, F. Richard
Xiong, Hui
contents In this paper, we propose the first Structure-from-Motion (SfM)-free deblurring 3D Gaussian Splatting method via event camera, dubbed DeblurSplat. We address the motion-deblurring problem in two ways. First, we leverage the pretrained capability of the dense stereo module (DUSt3R) to directly obtain accurate initial point clouds from blurred images. Without calculating camera poses as an intermediate result, we avoid the cumulative errors transfer from inaccurate camera poses to the initial point clouds' positions. Second, we introduce the event stream into the deblur pipeline for its high sensitivity to dynamic change. By decoding the latent sharp images from the event stream and blurred images, we can provide a fine-grained supervision signal for scene reconstruction optimization. Extensive experiments across a range of scenes demonstrate that DeblurSplat not only excels in generating high-fidelity novel views but also achieves significant rendering efficiency compared to the SOTAs in deblur 3D-GS.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18898
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeblurSplat: SfM-free 3D Gaussian Splatting with Event Camera for Robust Deblurring
Li, Pengteng
Lu, Yunfan
Song, Pinhao
Guo, Weiyu
Yao, Huizai
Yu, F. Richard
Xiong, Hui
Computer Vision and Pattern Recognition
In this paper, we propose the first Structure-from-Motion (SfM)-free deblurring 3D Gaussian Splatting method via event camera, dubbed DeblurSplat. We address the motion-deblurring problem in two ways. First, we leverage the pretrained capability of the dense stereo module (DUSt3R) to directly obtain accurate initial point clouds from blurred images. Without calculating camera poses as an intermediate result, we avoid the cumulative errors transfer from inaccurate camera poses to the initial point clouds' positions. Second, we introduce the event stream into the deblur pipeline for its high sensitivity to dynamic change. By decoding the latent sharp images from the event stream and blurred images, we can provide a fine-grained supervision signal for scene reconstruction optimization. Extensive experiments across a range of scenes demonstrate that DeblurSplat not only excels in generating high-fidelity novel views but also achieves significant rendering efficiency compared to the SOTAs in deblur 3D-GS.
title DeblurSplat: SfM-free 3D Gaussian Splatting with Event Camera for Robust Deblurring
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.18898