MotionGS : Compact Gaussian Splatting SLAM by Motion Filter

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Xinli, Zhang, Weidong, Liu, Ruonan, Han, Peng, Chen, Hongtian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913371640561664
author Guo, Xinli
Zhang, Weidong
Liu, Ruonan
Han, Peng
Chen, Hongtian
author_facet Guo, Xinli
Zhang, Weidong
Liu, Ruonan
Han, Peng
Chen, Hongtian
contents With their high-fidelity scene representation capability, the attention of SLAM field is deeply attracted by the Neural Radiation Field (NeRF) and 3D Gaussian Splatting (3DGS). Recently, there has been a surge in NeRF-based SLAM, while 3DGS-based SLAM is sparse. A novel 3DGS-based SLAM approach with a fusion of deep visual feature, dual keyframe selection and 3DGS is presented in this paper. Compared with the existing methods, the proposed tracking is achieved by feature extraction and motion filter on each frame. The joint optimization of poses and 3D Gaussians runs through the entire mapping process. Additionally, the coarse-to-fine pose estimation and compact Gaussian scene representation are implemented by dual keyframe selection and novel loss functions. Experimental results demonstrate that the proposed algorithm not only outperforms the existing methods in tracking and mapping, but also has less memory usage.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11129
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MotionGS : Compact Gaussian Splatting SLAM by Motion Filter
Guo, Xinli
Zhang, Weidong
Liu, Ruonan
Han, Peng
Chen, Hongtian
Computer Vision and Pattern Recognition
With their high-fidelity scene representation capability, the attention of SLAM field is deeply attracted by the Neural Radiation Field (NeRF) and 3D Gaussian Splatting (3DGS). Recently, there has been a surge in NeRF-based SLAM, while 3DGS-based SLAM is sparse. A novel 3DGS-based SLAM approach with a fusion of deep visual feature, dual keyframe selection and 3DGS is presented in this paper. Compared with the existing methods, the proposed tracking is achieved by feature extraction and motion filter on each frame. The joint optimization of poses and 3D Gaussians runs through the entire mapping process. Additionally, the coarse-to-fine pose estimation and compact Gaussian scene representation are implemented by dual keyframe selection and novel loss functions. Experimental results demonstrate that the proposed algorithm not only outperforms the existing methods in tracking and mapping, but also has less memory usage.
title MotionGS : Compact Gaussian Splatting SLAM by Motion Filter
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.11129