A Grid-Based Hierarchical Representation Method for Large-Scale Scene Based on 3DGS
Preprint
- 8 April 2025
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Efficient and realistic large-scale scene modeling is an important application of low-altitude remote sensing. Although the emerging 3DGS technology offers a simple process and realistic results, its high computational resource demands hinder direct application in large-scale 3D scene reconstruction. To address this, this paper proposes a novel grid-based scene segmentation technique in the process of reconstruction. Sparse point clouds, acting as an indirect input for 3DGS, are first processed by Z-Score and percentile-based filter to prepare the pure scene for segmentation. Then, through grid creation, grid partitioning, and grid merging, it forms rational and widely-applicable sub-grids and sub-scenes for training. Followed by integrating Hierarchy-GS's LOD strategy, this method achieves better large-scale reconstruction effect within limited computational resources. Experiments on multiple datasets show that this method matches others in single block reconstruction and excels in complete scene reconstruction, achieving superior results in PSNR, LPIPS, SSIM, and visualization quality.Keywords
All Related Versions
- Version 1, 2025-04-08, Preprints
- Published version: Remote Sensing, 17 (10), 1801.
This publication has 30 references indexed in Scilit:
- Scene reconstruction techniques for autonomous driving: a review of 3D Gaussian splattingArtificial Intelligence Review, 2024
- Multi-view stereo algorithms based on deep learning: a surveyMultimedia Tools and Applications, 2024
- SuperNeRF: High-Precision 3-D Reconstruction for Large-Scale ScenesIEEE Transactions on Geoscience and Remote Sensing, 2024
- Enhancing 3D reconstruction of textureless indoor scenes with IndoReal multi-view stereo (MVS)Automation in Construction, 2024
- Drone-NeRF: Efficient NeRF based 3D scene reconstruction for large-scale drone surveyImage and Vision Computing, 2024
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingACM Transactions on Graphics, 2023
- Instant neural graphics primitives with a multiresolution hash encodingACM Transactions on Graphics, 2022
- NeRFCommunications of the ACM, 2021
- DONeRF: Towards Real‐Time Rendering of Compact Neural Radiance Fields using Depth Oracle NetworksComputer Graphics Forum, 2021
- A Survey of Surface Reconstruction from Point CloudsComputer Graphics Forum, 2016