This repository contains a differentiable PlenOctree and renderer implementation as a PyTorch CUDA extension. It is used by our conversion and optimization code.

PlenOctrees for Real Time Rendering of Neural Radiance Fields
Alex Yu, Ruilong Li, Matthew Tancik, Hao Li, Ren Ng, Angjoo Kanazawa

https://alexyu.net/plenoctrees

@inproceedings{yu2021plenoctrees,
      title={{PlenOctrees} for Real-time Rendering of Neural Radiance Fields},
      author={Alex Yu and Ruilong Li and Matthew Tancik and Hao Li and Ren Ng and Angjoo Kanazawa},
      year={2021},
      booktitle={ICCV},
}

Please also refer to the following repositories

• NeRF-SH training and PlenOctree extraction: https://github.com/sxyu/plenoctree
• C++ volume renderer https://github.com/sxyu/volrend

pip install svox

Please see https://svox.readthedocs.io

If you get SIGSEGV upon importing, check that your CUDA runtime and PyTorch CUDA versions match. That is, nvcc --version should match (Python) torch.version.cuda

SVOX stands for sparse voxel octree extension.