Rip-NeRF
Rip-NeRF copied to clipboard
Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids
Rip-NeRF
Official PyTorch implementation of the paper:
Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids
SIGGRAPH 2024
Junchen Liu*, Wenbo Hu*, Zhuo Yang*, Jianteng Chen, Guoliang Wang, Xiaoxue Chen, Yantong Cai, Huang-ang Gao, Hao Zhao
Installation
We use Python 3.9. Please install the following dependencies first
And then install the following dependencies using pip
pip3 install absl-py \
gin-config==0.5.0 \
loguru==0.6.0 \
matplotlib \
nerfacc==0.3.5 \
numpy==1.23.3 \
open3d==0.16.0 \
opencv-python==4.6.0.66 \
Pillow==9.2.0 \
rich==12.6.0 \
tensorboardX \
termcolor \
torchmetrics==0.10.0 \
torchmetrics[image] \
torchtyping==0.1.4 \
tqdm==4.64.1
Data
nerf_synthetic dataset
Please download and unzip nerf_synthetic.zip
from the NeRF official Google Drive.
Generate multiscale dataset
Please generate it by
python scripts/convert_blender_data.py --blenderdir /path/to/nerf_synthetic --outdir /path/to/nerf_synthetic_multiscale
Training and evaluation
python main.py --ginc config_files/ms_blender.gin
Citation
If you find the code useful for your work, please star this repo and consider citing:
@inproceedings{liu2024ripnerf,
title={Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids},
author={Liu, Junchen and Hu, Wenbo and Yang, Zhuo and Chen, Jianteng and Wang, Guoliang and Chen, Xiaoxue and Cai, Yantong and Gao, Huan-ang and Zhao, Hao},
year={2024},
booktitle={SIGGRAPH'24 Conference Proceedings},
}