最近一直在做NeRF相关的项目,其中LLFF前向数据集,是NeRF常用数据集,本文讲下怎么对NeRF数据进行处理
几个重要的链接地址
- github-llff : GitHub - Fyusion/LLFF: Code release for Local Light Field Fusion at SIGGRAPH 2019
- github-yen: GitHub - yenchenlin/nerf-pytorch: A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
- github-2020eccv: GitHub - bmild/nerf: Code release for NeRF (Neural Radiance Fields)
这是一个利用预训练好的 模型,来进行render的demo。
demo.sh 的内容如下:
# Use COLMAP to compute 6DoF camera poses
python imgs2poses.py data/testscene/
# Create MPIs using pretrained network
python imgs2mpis.py \
data/testscene/ \
data/testscene/mpis_360 \
--height 360
# Generate smooth path of poses for new views
mkdir data/testscene/outputs/
python imgs2renderpath.py \
data/testscene/ \
data/testscene/outputs/test_path.txt \
--spiral
cd cuda_renderer && make && cd ..
# Render novel views using input MPIs and poses
cuda_renderer/cuda_renderer \
data/testscene/mpis_360 \
data/testscene/outputs/test_path.txt \
data/testscene/outputs/test_vid.mp4 \
360 .8 18
运行nvidia-docker run --rm --volume /:/host --workdir /host$PWD tf_colmap bash demo.sh
完成后,输出文件如下: