MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bui, Minh-Quan Viet, Park, Jongmin, Bello, Juan Luis Gonzalez, Moon, Jaeho, Oh, Jihyong, Kim, Munchurl
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914178003894272
author Bui, Minh-Quan Viet
Park, Jongmin
Bello, Juan Luis Gonzalez
Moon, Jaeho
Oh, Jihyong
Kim, Munchurl
author_facet Bui, Minh-Quan Viet
Park, Jongmin
Bello, Juan Luis Gonzalez
Moon, Jaeho
Oh, Jihyong
Kim, Munchurl
contents We present MoBGS, a novel motion deblurring 3D Gaussian Splatting (3DGS) framework capable of reconstructing sharp and high-quality novel spatio-temporal views from blurry monocular videos in an end-to-end manner. Existing dynamic novel view synthesis (NVS) methods are highly sensitive to motion blur in casually captured videos, resulting in significant degradation of rendering quality. While recent approaches address motion-blurred inputs for NVS, they primarily focus on static scene reconstruction and lack dedicated motion modeling for dynamic objects. To overcome these limitations, our MoBGS introduces a novel Blur-adaptive Latent Camera Estimation (BLCE) method using a proposed Blur-adaptive Neural Ordinary Differential Equation (ODE) solver for effective latent camera trajectory estimation, improving global camera motion deblurring. In addition, we propose a Latent Camera-induced Exposure Estimation (LCEE) method to ensure consistent deblurring of both a global camera and local object motions. Extensive experiments on the Stereo Blur dataset and real-world blurry videos show that our MoBGS significantly outperforms the very recent methods, achieving state-of-the-art performance for dynamic NVS under motion blur.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15122
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video
Bui, Minh-Quan Viet
Park, Jongmin
Bello, Juan Luis Gonzalez
Moon, Jaeho
Oh, Jihyong
Kim, Munchurl
Computer Vision and Pattern Recognition
We present MoBGS, a novel motion deblurring 3D Gaussian Splatting (3DGS) framework capable of reconstructing sharp and high-quality novel spatio-temporal views from blurry monocular videos in an end-to-end manner. Existing dynamic novel view synthesis (NVS) methods are highly sensitive to motion blur in casually captured videos, resulting in significant degradation of rendering quality. While recent approaches address motion-blurred inputs for NVS, they primarily focus on static scene reconstruction and lack dedicated motion modeling for dynamic objects. To overcome these limitations, our MoBGS introduces a novel Blur-adaptive Latent Camera Estimation (BLCE) method using a proposed Blur-adaptive Neural Ordinary Differential Equation (ODE) solver for effective latent camera trajectory estimation, improving global camera motion deblurring. In addition, we propose a Latent Camera-induced Exposure Estimation (LCEE) method to ensure consistent deblurring of both a global camera and local object motions. Extensive experiments on the Stereo Blur dataset and real-world blurry videos show that our MoBGS significantly outperforms the very recent methods, achieving state-of-the-art performance for dynamic NVS under motion blur.
title MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.15122