SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embedding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wen, Tianci, Liu, Zhiang, Fang, Yongchun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915384749195264
author Wen, Tianci
Liu, Zhiang
Fang, Yongchun
author_facet Wen, Tianci
Liu, Zhiang
Fang, Yongchun
contents 3D Gaussian splatting (3D-GS) has recently revolutionized novel view synthesis in the simultaneous localization and mapping (SLAM) problem. However, most existing algorithms fail to fully capture the underlying structure, resulting in structural inconsistency. Additionally, they struggle with abrupt appearance variations, leading to inconsistent visual quality. To address these problems, we propose SEGS-SLAM, a structure-enhanced 3D Gaussian Splatting SLAM, which achieves high-quality photorealistic mapping. Our main contributions are two-fold. First, we propose a structure-enhanced photorealistic mapping (SEPM) framework that, for the first time, leverages highly structured point cloud to initialize structured 3D Gaussians, leading to significant improvements in rendering quality. Second, we propose Appearance-from-Motion embedding (AfME), enabling 3D Gaussians to better model image appearance variations across different camera poses. Extensive experiments on monocular, stereo, and RGB-D datasets demonstrate that SEGS-SLAM significantly outperforms state-of-the-art (SOTA) methods in photorealistic mapping quality, e.g., an improvement of $19.86\%$ in PSNR over MonoGS on the TUM RGB-D dataset for monocular cameras. The project page is available at https://segs-slam.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2501_05242
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embedding
Wen, Tianci
Liu, Zhiang
Fang, Yongchun
Computer Vision and Pattern Recognition
68T40(Primary)68T45, 68U99 (Secondary)
I.4.8; I.3.7
3D Gaussian splatting (3D-GS) has recently revolutionized novel view synthesis in the simultaneous localization and mapping (SLAM) problem. However, most existing algorithms fail to fully capture the underlying structure, resulting in structural inconsistency. Additionally, they struggle with abrupt appearance variations, leading to inconsistent visual quality. To address these problems, we propose SEGS-SLAM, a structure-enhanced 3D Gaussian Splatting SLAM, which achieves high-quality photorealistic mapping. Our main contributions are two-fold. First, we propose a structure-enhanced photorealistic mapping (SEPM) framework that, for the first time, leverages highly structured point cloud to initialize structured 3D Gaussians, leading to significant improvements in rendering quality. Second, we propose Appearance-from-Motion embedding (AfME), enabling 3D Gaussians to better model image appearance variations across different camera poses. Extensive experiments on monocular, stereo, and RGB-D datasets demonstrate that SEGS-SLAM significantly outperforms state-of-the-art (SOTA) methods in photorealistic mapping quality, e.g., an improvement of $19.86\%$ in PSNR over MonoGS on the TUM RGB-D dataset for monocular cameras. The project page is available at https://segs-slam.github.io/.
title SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embedding
topic Computer Vision and Pattern Recognition
68T40(Primary)68T45, 68U99 (Secondary)
I.4.8; I.3.7
url https://arxiv.org/abs/2501.05242