Micro-macro Gaussian Splatting with Enhanced Scalability for Unconstrained Scene Reconstruction

TL;DR

This paper introduces SMW-GS, a scalable Gaussian Splatting method that decomposes scene representations for improved 3D reconstruction across diverse scales and complex scenes, especially in large urban environments.

Contribution

The paper presents a novel multi-scale Gaussian Splatting approach with wavelet-based sampling and a large-scale scene promotion strategy for enhanced scalability and reconstruction quality.

Findings

Outperforms existing methods in large-scale urban scenes

Achieves higher reconstruction quality and detail

Demonstrates scalability in expansive environments

Abstract

Reconstructing 3D scenes from unconstrained image collections poses significant challenges due to variations in appearance. In this paper, we propose Scalable Micro-macro Wavelet-based Gaussian Splatting (SMW-GS), a novel method that enhances 3D reconstruction across diverse scales by decomposing scene representations into global, refined, and intrinsic components. SMW-GS incorporates the following innovations: Micro-macro Projection, which enables Gaussian points to sample multi-scale details with improved diversity; and Wavelet-based Sampling, which refines feature representations using frequency-domain information to better capture complex scene appearances. To achieve scalability, we further propose a large-scale scene promotion strategy, which optimally assigns camera views to scene partitions by maximizing their contributions to Gaussian points, achieving consistent and high-quality reconstructions even in expansive environments. Extensive experiments demonstrate that SMW-GS significantly outperforms existing methods in both reconstruction quality and scalability, particularly excelling in large-scale urban environments with challenging illumination variations. Project is available at https://github.com/Kidleyh/SMW-GS.