CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction
This addresses the challenge of practical large-scale scene reconstruction for applications like urban modeling, though it appears incremental by building on existing Gaussian Splatting methods.
The paper tackles the problem of high memory costs and time consumption in large-scale 3D scene reconstruction using Gaussian Splatting, achieving fast and scalable high-fidelity surface reconstruction with reduced GPU memory usage.
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}.