A General NeRF Acceleration Toolbox.
Reason this release was yanked:
Bug
Project description
NerfAcc
This is a tiny toolbox for accelerating NeRF training & rendering using PyTorch CUDA extensions. Plug-and-play for most of the NeRFs!
Installation
pip install nerfacc
Examples:
Before running those example scripts, please check the script about which dataset it is needed, and download the dataset first.
# Instant-NGP NeRF in 4.5 minutes.
# See results at here: https://www.nerfacc.com/en/latest/examples/ngp.html
python examples/train_ngp_nerf.py --train_split trainval --scene lego
# Vanilla MLP NeRF in 1 hour.
# See results at here: https://www.nerfacc.com/en/latest/examples/vanilla.html
python examples/train_mlp_nerf.py --train_split train --scene lego
# T-NeRF for Dynamic objects in 1 hour.
# See results at here: https://www.nerfacc.com/en/latest/examples/dnerf.html
python examples/train_mlp_dnerf.py --train_split train --scene lego
# Unbounded scene in 1 hour.
# See results at here: https://www.nerfacc.com/en/latest/examples/unbounded.html
python examples/train_ngp_nerf.py --train_split train --scene garden --auto_aabb --unbounded --cone_angle=0.004
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nerfacc-0.1.8.tar.gz
(30.7 kB
view hashes)
Built Distribution
nerfacc-0.1.8-py3-none-any.whl
(37.0 kB
view hashes)