CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction

TL;DR

CoSurfGS introduces a distributed learning framework for large-scale 3D surface reconstruction, enabling efficient, high-fidelity, and scalable scene modeling with reduced memory use and faster processing.

Contribution

It presents a novel multi-agent collaborative framework with local model compression and aggregation schemes for large scene 3D reconstruction.

Findings

Achieves fast and scalable high-fidelity surface reconstruction.

Reduces GPU memory consumption during large-scale scene modeling.

Demonstrates effectiveness on urban and complex scene datasets.

Abstract

3D Gaussian Splatting (3DGS) has demonstrated impressive performance in scene reconstruction. However, most existing GS-based surface reconstruction methods focus on 3D objects or limited scenes. Directly applying these methods to large-scale scene reconstruction will pose challenges such as high memory costs, excessive time consumption, and lack of geometric detail, which makes it difficult to implement in practical applications. To address these issues, we propose a multi-agent collaborative fast 3DGS surface reconstruction framework based on distributed learning for large-scale surface reconstruction. Specifically, we develop local model compression (LMC) and model aggregation schemes (MAS) to achieve high-quality surface representation of large scenes while reducing GPU memory consumption. Extensive experiments on Urban3d, MegaNeRF, and BlendedMVS demonstrate that our proposed method can achieve fast and scalable high-fidelity surface reconstruction and photorealistic rendering. Our project page is available at \url{https://gyy456.github.io/CoSurfGS}.