DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus

TL;DR

This paper introduces DOGS, a distributed training method for 3D Gaussian Splatting that significantly accelerates training on large-scale scenes while maintaining high rendering quality by using scene decomposition and Gaussian consensus.

Contribution

The paper proposes a novel distributed training framework for 3D Gaussian Splatting using scene decomposition and ADMM, enabling faster training on large scenes with maintained quality.

Findings

Training time reduced by over 6 times on large scenes.

Achieves state-of-the-art rendering quality.

Maintains stability and convergence through Gaussian consensus.

Abstract

The recent advances in 3D Gaussian Splatting (3DGS) show promising results on the novel view synthesis (NVS) task. With its superior rendering performance and high-fidelity rendering quality, 3DGS is excelling at its previous NeRF counterparts. The most recent 3DGS method focuses either on improving the instability of rendering efficiency or reducing the model size. On the other hand, the training efficiency of 3DGS on large-scale scenes has not gained much attention. In this work, we propose DoGaussian, a method that trains 3DGS distributedly. Our method first decomposes a scene into K blocks and then introduces the Alternating Direction Method of Multipliers (ADMM) into the training procedure of 3DGS. During training, our DOGS maintains one global 3DGS model on the master node and K local 3DGS models on the slave nodes. The K local 3DGS models are dropped after training and we only query the global 3DGS model during inference. The training time is reduced by scene decomposition, and the training convergence and stability are guaranteed through the consensus on the shared 3D Gaussians. Our method accelerates the training of 3DGS by 6+ times when evaluated on large-scale scenes while concurrently achieving state-of-the-art rendering quality. Our code is publicly available at https://github.com/AIBluefisher/DOGS.