SealD-NeRF: Interactive Pixel-Level Editing for Dynamic Scenes by Neural Radiance Fields Video: https://youtu.be/-1ZNdfG390E
git clone --recursive https://github.com/ashawkey/torch-ngp.git
cd torch-ngp
pip install -r requirements.txt
conda env create -f environment.yml
conda activate torch-ngp
By default, we use load to build the extension at runtime. However, this may be inconvenient sometimes. Therefore, we also provide the setup.py to build each extension:
# install all extension modules
bash scripts/install_ext.sh
# if you want to install manually, here is an example:
cd raymarching
python setup.py build_ext --inplace # build ext only, do not install (only can be used in the parent directory)
pip install . # install to python path (you still need the raymarching/ folder, since this only install the built extension.)
Train an NGP/TensoRF model following the instructions of torch-ngp#usage. For example:
python main_dnerf.py data/dnerf/jumpingjacks --workspace trial_dnerf_jumpingjacks -O --bound 1.0 --scale 0.8 --dt_gamma 0
python main_seald.py data/dnerf/jumpingjacks --workspace trial_dnerf_jumpingjacks -O --bound 1.0 --scale 0.8 --dt_gamma 0 --gui --teacher_workspace trial_seald_jumping