pyRad🤘

The all-in-one repo for NeRFs

• Quickstart
• Supported Features
• Benchmarked Model Architectures

Quickstart

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 see our docs.

1. Installation: Setup the environment

This repository is tested with CUDA 11.3. Make sure to install Conda before preceding.

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 pyrad python=3.8.13
conda activate pyrad

# Clone the repo
git clone git@github.com:plenoptix/pyrad.git

# Install dependencies
cd pyrad
pip install -r environment/requirements.txt

# Install pyrad as a library
pip install -e .

# Install library with CUDA support. Change setup.py to `USE_CUDA = True` and then
python setup.py develop

# Install tiny-cuda-nn (tcnn) to use with the graph_instant_ngp.yaml config
pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch

# Run the test cases
pytest tests

2. Getting the data

Download the original NeRF dataset and unfold it in the following format. This is for the blender dataset type. We support the major datasets and allow users to create their own dataset, described in detail here.

|─ pyrad/
   ├─ data/
   |  ├─ blender/
   |     ├─ fern/
   |     ├─ lego/
         ...
      |- <dataset_format>/
         |- <scene>
         ...

3. Training a model

To run with all the defaults, e.g. vanilla nerf method with the blender lego image

# Run a vanilla nerf model.
python scripts/run_train.py

# Run a faster version with instant ngp using tcnn (without the viewer).
python scripts/run_train.py --config-name=graph_instant_ngp.yaml

# Run with the viewer. However, you'll have to start the viewer server first. (See the docs.)
python scripts/run_train.py --config-name=graph_instant_ngp.yaml viewer.enable=true

With support for Hydra, you can run with other configurations by changing appropriate configs defined in configs/ or by setting flags via command-line arguments.

4. Visualizing training runs

We support multiple methods to visualize training, the default configuration uses Tensorboard. More information on logging can be found here.

viewer:
  enable: true

tensorboard --logdir outputs

# or the following
export TENSORBOARD_PORT=<port>
bash environment/run_tensorboard.sh

logging:
    writer:
        WandbWriter

5. Rendering a trajectories during inference

python scripts/run_eval.py --method=traj --traj=spiral --output-filename=output.mp4 --config-name=graph_instant_ngp.yaml trainer.resume_train.load_dir=outputs/blender_lego/instant_ngp/2022-07-07_230905/checkpoints

6. In-depth guide

For a more in-depth tutorial on how to modify/implement your own NeRF Graph, please see our walk-through.

Supported Features

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!

:metal: Support for Hydra config structure

:metal: Support for multiple logging interfaces

:metal: Built-in support for profiling code

:metal: Benchmarking scripts

:metal: Speed up your code with Tiny Cuda NN

Benchmarked Model Architectures