The all-in-one repo for NeRFs
All-in-one repository for state-of-the-art NeRFs.
Nerfactory provides a simple API that allows for a seamless and simplified end-to-end process of creating, training, and visualizing NeRFs. The library supports a more interpretable implementation of NeRFs by modularizing each component. With more modular NeRFs, not only does your code become far more user-friendly, but using this framework also makes it easier for the community to build upon your implementation.
It’s as simple as plug and play with Nerfactory!
Ontop of our API, we are commited to providing learning resources to help you understand the basics of (if you're just getting start), and keep up-to-date with (if you're a seasoned veteran) all things NeRF. As researchers, we know just how hard it is to get onboarded with this next-gen technology. So we're here to help with tutorials, documentation, and more!
Finally, have feature requests? Want to add your brand-spankin'-new NeRF model? Have a new dataset? We welcome any and all contributions!
We hope Nerfactory enables you to build faster 🔨 learn together 📚 and contribute to our NeRF community 💖.
The quickstart will help you get started with the default vanilla nerf trained on the classic blender lego scene. For more complex changes (e.g. running with your own data/ setting up a new NeRF graph, please refer to our references.
This repository is tested with CUDA 11.3. Make sure to install Conda before preceding.
Installing Conda
This step is fairly self-explanatory, but here are the basic steps. You can also find countless tutorials online.
cd /path/to/install/miniconda
mkdir -p miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda3/miniconda.sh
bash miniconda3/miniconda.sh -b -u -p miniconda3
rm -rf miniconda/miniconda.sh
Create the python environment
conda create --name nerfactory python=3.8.13
conda activate nerfactory
Clone the repo
git clone [email protected]:plenoptix/nerfactory.git
cd nerfactory
Install dependencies and nerfactory as a library
python -m pip install --upgrade pip
pip install -e .
Install tiny-cuda-nn (tcnn) to run instant_ngp
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 -f https://download.pytorch.org/whl/torch_stable.html
pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch
Run the test cases
pytest tests
Download the original NeRF Blender dataset. We support the major datasets and allow users to create their own dataset, described in detail here.
python scripts/downloads/download_data.py --dataset=blender
Use --help to view all currently available datasets. The resulting script should download and unpack the dataset as follows:
|─ nerfactory/
├─ data/
| ├─ blender/
| ├─ fern/
| ├─ lego/
...
|- <dataset_format>/
|- <scene>
...
To run with all the defaults, e.g. vanilla nerf method with the blender lego image
# To see what models are available.
python scripts/run_train.py --help
# Run a vanilla nerf model.
python scripts/run_train.py vanilla_nerf
# Run a faster version with instant ngp using tcnn (without the viewer).
python scripts/run_train.py instant_ngp
Make sure to forward a port for the websocket to localhost. The default port is 7007, which you should be expose to localhost:7007.
# with the default port
python scripts/run_train.py instant_ngp --viewer.enable
# with a specified websocket port
python scripts/run_train.py instant_ngp --viewer.enable --viewer.websocket-port=7008
# with the viewer bridge server as a separate process
# in one terminal, start the bridge server:
viewer-bridge-server # or equivalently, python scripts/run_viewer_bridge_server.py
# in another terminal, start training:
python scripts/run_train.py instant_ngp --viewer.enable --viewer.no-launch-bridge-serverWe support multiple methods to visualize training, the default configuration uses Tensorboard. More information on logging can be found here.
Real-time Viewer
We have developed our own Real-time web viewer, more information can be found here. This viewer runs during training and is designed to work with models that have fast rendering pipelines.
To turn on the viewer, simply add the flag --viewer.enable.
Tensorboard
If you run everything with the default configuration we log all training curves, test images, and other stats. Once the job is launched, you will be able to track training by launching the tensorboard in your base experiment directory (Default: outputs/).
tensorboard --logdir outputs/Weights & Biases
We support logging to weights and biases. To enable wandb logging, add the flag --logging.writer.1.enable.
python scripts/run_eval.py render-trajectory --load-config=outputs/blender_lego/instant_ngp/2022-07-07_230905/config.yml--traj=spiral --output-path=output.mp4
For a more in-depth tutorial on how to modify/implement your own NeRF Graph, please see our walk-through.
| Section | Description |
|---|---|
| Documentation | Full API documentation and tutorials |
| Interactive Guides | Go-to spot for learning how NeRFs and each of its modules work. |
| Quick tour | Example script on how to navigate Nerfactory from install, train, to test. |
| Creating pipelines | Learn how to easily build new neural rendering pipelines by using and/or implementing new modules. |
| Creating datsets | Have a new dataset? Learn how to use it with Nerfactory. |
| Mobile Capture to NerF | Step-by-step tutorial on how to create beautiful renders with just your phone. |
| Contributing | Walk-through for how you can start contributing now. |
| Slack | Join our community to discuss more. We would love to hear from you! |
We provide the following support strucutures to make life easier for getting started with NeRFs. For a full description, please refer to our features page.
If you are looking for a feature that is not currently supported, please do not hesitate to contact the Plenoptix team!
- 🔎 Web-based visualizer that allows you to:
- Visualize training in real-time + interact with the scene
- Create and render out scenes with custom camera trajectories
- View different output types
- And more!
- ✏️ Support for multiple logging interfaces (Tensorboard, Wandb), code profiling, and other built-in debugging tools
- 📈 Easy-to-use benchmarking scripts on the Blender dataset
- 📱 Full pipeline support (w/ Colmap or Record3D) for going from a video on your phone to a full 3D render. Follow our step-by-step tutorial. (TODO: walk-through page on end-to-end pipeline from capture -> render)
TODO: insert some gallery stuff here (gifs/pretty pictures w/ visualizer) TODO: For more see gallery