营销型网站建设专家代发新闻稿最大平台

目录

简介

1 概要和依赖

2 实际安装测试

拉取代码

 CUDA环境对安装的影响

单独安装pytorch的命令

3 使⽤⾃⼰的数据调⽤算法

colmap安装

训练

交互式可视化

---

简介

论⽂：3D Gaussian Splatting for Real-Time Radiance Field Rendering

项⽬地址： https://github.com/graphdeco-inria/gaussian-splatting

1 概要和依赖

如果在Windows⽤，有视频逐步骤指导，参考 youtube视频链接

本⽂档后续内容都是建⽴在Ubuntu上进⾏使⽤的

下⾯内容都摘⾃README.md，纯英⽂，我们在第⼆节将展⽰实测安装算法遇到的问题和全流程

1.1 Codebase

The codebase has 4 main components:

•

A PyTorch-based optimizer to produce a 3D Gaussian model from SfM inputs

•

A network viewer that allows to connect to and visualize the optimization process

•

An OpenGL-based real-time viewer to render trained models in real-time.

•

A script to help you turn your own images into optimization-ready SfM data sets

The components have different requirements w.r.t. both hardware and software. They have

been tested on Windows 10 and Ubuntu Linux 22.04. Instructions for setting up and running

each of them are found in the sections below.

作者只在Ubuntu 22.04做了测试；实际我们在Ubuntu 18.04和20.04进⾏了测试

在Ubuntu18.04可以完成训练，但⽆法可视化；Ubuntu20.04可以可视化

1.3 Software Requirements

•

Conda (recommended for easy setup)

•

C++ Compiler for PyTorch extensions (we used Visual Studio 2019 for Windows)

•

CUDA SDK 11 for PyTorch extensions, install after Visual Studio (we used 11.8, known issues

with 11.6)

•

C++ Compiler and CUDA SDK must be compatible

CUDA 11.8很重要

关于Conda环境：

Conda环境（相⽐Miniconda，更推荐Anaconda）安装参考链接：

【精选】Ubuntu:conda的安装与使⽤_乌班图使⽤conda-CSDN博客

Anaconda | The World’s Most Popular Data Science Platform

2 实际安装测试

拉取代码

使⽤--recursive把submodules给全部拉取下来，这个很重要；不加的话，后续有的东西装不上

git clone [e-mail]:graphdeco-inria/gaussian-splatting.git --recursive

git clone https://github.com/graphdeco-inria/gaussian-splatting --recursive

如果submodule安装失败，可能出现以下报错 <