NerfAcc: A General NeRF Acceleration Toolbox
This provides a practical tool for researchers and practitioners working with NeRFs to speed up rendering, but it is incremental as it builds on existing methods.
The authors tackled the problem of slow volumetric rendering in neural radiance fields (NeRFs) by developing NerfAcc, a general acceleration toolbox that extends techniques from Instant-NGP to support bounded static, dynamic, and unbounded scenes, resulting in a plug-and-play solution with a user-friendly Python API.
We propose NerfAcc, a toolbox for efficient volumetric rendering of radiance fields. We build on the techniques proposed in Instant-NGP, and extend these techniques to not only support bounded static scenes, but also for dynamic scenes and unbounded scenes. NerfAcc comes with a user-friendly Python API, and is ready for plug-and-play acceleration of most NeRFs. Various examples are provided to show how to use this toolbox. Code can be found here: https://github.com/KAIR-BAIR/nerfacc. Note this write-up matches with NerfAcc v0.3.5. For the latest features in NerfAcc, please check out our more recent write-up at arXiv:2305.04966