NViST运行笔记

文章标题：

NViST: In the Wild New View Synthesis from a Single Image with Transformers 

1. 环境配置

创建环境

conda create -n nvist python=3.9

 进入环境

conda activate nvist

安装torch torchvision torchaudio

pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cu121

 安装其它依赖

pip install tqdm scikit-image opencv-python configargparse lpips imageio-ffmpeg lpips tensorboard torch_efficient_distloss

pip install easydict timm plyfile matplotlib kornia accelerate

pip install tensorflow pandas
pip install git+https://github.com/google/nerfies.git@v2
pip install "git+https://github.com/google/nerfies.git#egg=pycolmap&subdirectory=third_party/pycolmap"

2. 数据下载与预处理

2.1. 获取下载地址和密码

点击链接 https://docs.google.com/forms/d/e/1FAIpQLSfU9BkV1hY3r75n5rc37IvlzaK2VFYbdsvohqPGAjb2YWIbUg/viewform

填写所有的必填项

得到下载地址和密码

点击链接并输入密码

2.2. 使用chrome下载

进入开发者模式（Windows和Linux快捷键Ctrl+Shift+I，MacOS快捷键command+option+J）

进入Network tab

选择若干文件，点击下载

如果是下载到桌面客户端，则等待下载完成即可；如果想下载到远端，则需要继续下面的步骤。

看到一个类似"download.aspx?..."的条目，右键点击→Copy→Copy as cURL

Paste the copied content directly in the terminal and append --output mvi_xxx.zip, since the terminal isn't capable of showing binary data.

2.3. 数据预处理

python preprocess/downsample_imgs --data_dir [data directory]

3. 训练

4. 推理

参考文献

GitHub - wbjang/nvist_official: (CVPR 2024) NViST: In the wild New View Synthesis from a Single Image with Transformers