Saved in:
Bibliographic Details
Main Authors: Wu, YuanZheng, Liu, Jin, Ji, Shunping
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.00381
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916405394276352
author Wu, YuanZheng
Liu, Jin
Ji, Shunping
author_facet Wu, YuanZheng
Liu, Jin
Ji, Shunping
contents Recently, 3D Gaussian Splatting (3DGS) has demonstrated excellent ability in small-scale 3D surface reconstruction. However, extending 3DGS to large-scale scenes remains a significant challenge. To address this gap, we propose a novel 3DGS-based method for large-scale surface reconstruction using aerial multi-view stereo (MVS) images, named Aerial Gaussian Splatting (AGS). First, we introduce a data chunking method tailored for large-scale aerial images, making 3DGS feasible for surface reconstruction over extensive scenes. Second, we integrate the Ray-Gaussian Intersection method into 3DGS to obtain depth and normal information. Finally, we implement multi-view geometric consistency constraints to enhance the geometric consistency across different views. Our experiments on multiple datasets demonstrate, for the first time, the 3DGS-based method can match conventional aerial MVS methods on geometric accuracy in aerial large-scale surface reconstruction, and our method also beats state-of-the-art GS-based methods both on geometry and rendering quality.
format Preprint
id arxiv_https___arxiv_org_abs_2409_00381
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle 3D Gaussian Splatting for Large-scale Surface Reconstruction from Aerial Images
Wu, YuanZheng
Liu, Jin
Ji, Shunping
Computer Vision and Pattern Recognition
Recently, 3D Gaussian Splatting (3DGS) has demonstrated excellent ability in small-scale 3D surface reconstruction. However, extending 3DGS to large-scale scenes remains a significant challenge. To address this gap, we propose a novel 3DGS-based method for large-scale surface reconstruction using aerial multi-view stereo (MVS) images, named Aerial Gaussian Splatting (AGS). First, we introduce a data chunking method tailored for large-scale aerial images, making 3DGS feasible for surface reconstruction over extensive scenes. Second, we integrate the Ray-Gaussian Intersection method into 3DGS to obtain depth and normal information. Finally, we implement multi-view geometric consistency constraints to enhance the geometric consistency across different views. Our experiments on multiple datasets demonstrate, for the first time, the 3DGS-based method can match conventional aerial MVS methods on geometric accuracy in aerial large-scale surface reconstruction, and our method also beats state-of-the-art GS-based methods both on geometry and rendering quality.
title 3D Gaussian Splatting for Large-scale Surface Reconstruction from Aerial Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.00381