aibluefisher / dogaussian

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

DoGaussian

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

[Project Page | arXiv]

1. Introduction

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.

Cite

If you find this project useful for your research, please consider citing our paper:

@inproceedings{yuchen2024dogaussian,
    title={DoGaussian: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus},
    author={Yu Chen, Gim Hee Lee},
    booktitle={arXiv},
    year={2024},
}

dogaussian's Issues

About code

Great work! I want to know do you have a plan to release the code? I’m eager to give it a try.

Question about the performance reported in the paper

Thanks for your nice work!

I have a simple question regarding the performance reported in the paper.

For example, as for the ''Building'' dataset, there are 1920 training images and 20 testing images.
I would like to ask if the reported performance were tested on these 20 testing images?
Did these 20 images participate in the training?

Looking forward to your reply.

A small spelling issue in paper