3D Gaussian Splatting for Fine-Detailed Surface Reconstruction in Large-Scale Scene

TL;DR

This paper presents a novel large-scale 3D surface reconstruction method using Gaussian splatting, incorporating a coarse-to-fine strategy, adaptive scene partitioning, and appearance modeling to achieve high-fidelity results in outdoor environments.

Contribution

It introduces a scalable, detailed 3D reconstruction approach with scene partitioning and appearance modeling, outperforming existing methods on large outdoor datasets.

Findings

Outperforms existing NeRF-based and Gaussian-based methods

Achieves high-fidelity visual results and accurate surface reconstruction

Effective in outdoor large-scale scene reconstruction

Abstract

Recent developments in 3D Gaussian Splatting have made significant advances in surface reconstruction. However, scaling these methods to large-scale scenes remains challenging due to high computational demands and the complex dynamic appearances typical of outdoor environments. These challenges hinder the application in aerial surveying and autonomous driving. This paper proposes a novel solution to reconstruct large-scale surfaces with fine details, supervised by full-sized images. Firstly, we introduce a coarse-to-fine strategy to reconstruct a coarse model efficiently, followed by adaptive scene partitioning and sub-scene refining from image segments. Additionally, we integrate a decoupling appearance model to capture global appearance variations and a transient mask model to mitigate interference from moving objects. Finally, we expand the multi-view constraint and introduce a single-view regularization for texture-less areas. Our experiments were conducted on the publicly available dataset GauU-Scene V2, which was captured using unmanned aerial vehicles. To the best of our knowledge, our method outperforms existing NeRF-based and Gaussian-based methods, achieving high-fidelity visual results and accurate surface from full-size image optimization. Open-source code will be available on GitHub.