【orbslam2+nerf】

1. 需要安装

1. cuda
2. cudnn
3. eigen-3.4.0
4. opencv4.4以上（推荐opencv-4.5.5）
5. 需要gui，还要安装glfw：

sudo apt-get install libglfw3-dev libgl1-mesa-dev libglu1-mesa-dev libglew-dev

2. run

1. 下载源码：给你了
2. 解压Vocabulary

cd Vocabulary
tar zxf ORBvoc.txt.tar.gz

3. Build with GUI

cmake -B build -DCMAKE_BUILD_TYPE=Release .
cmake --build build --parallel $(nproc --all)

或Build without GUI

cmake -B build -DCMAKE_BUILD_TYPE=Release -DORBEEZ_BUILD_WITH_GUI=OFF .
cmake --build build --parallel $(nproc --all)

4. 下载数据集TUM fr3/office Dataset

wget https://vision.in.tum.de/rgbd/dataset/freiburg3/rgbd_dataset_freiburg3_long_office_household.tgz --no-check-certificate
tar -xvzf rgbd_dataset_freiburg3_long_office_household.tgz

5. 运行单目

./build/mono_tum Vocabulary/ORBvoc.txt configs/Monocular/TUM/freiburg3_office.yaml ./rgbd_dataset_freiburg3_long_office_household/