nerfstudio 基本使用操作

使用之前，需要安装一下colmap，其中包括编译cere

基于colmap制作数据集

ns-process-data {video,images,polycam,record3d} --data {DATA_PATH} --output-dir {PROCESSED_DATA_DIR}

Training on your data

ns-train nerfacto --data {PROCESSED_DATA_DIR}

此外，需要使用调整camera的角度来生成高清版本的视频

ns-render --load-config outputs/big_room/nerfacto/2023-04-21_121802/config.yml --traj filename --camera-path-filename data/nerfstudio/big_room/camera_paths/bigroom.json --output-path renders/big_room/bigroom.mp4

Resume from checkpoint / visualize existing run

It is possible to load a pretrained model by running

ns-train nerfacto --data data/nerfstudio/poster --load-dir {outputs/.../nerfstudio_models}

This will automatically start training. If you do not want it to train, add --viewer.start-train False to your training command.