NerfingMVS

For CS231A course project, a modified version of orginial paper: Uses docker for COLMAP, and tests on different dataset.

NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
Yi Wei, Shaohui Liu, Yongming Rao, Wang Zhao, Jiwen Lu, Jie Zhou
ICCV 2021 (Oral Presentation)

Installation

• Pull NerfingMVS repo.

  git clone --recursive git@github.com:weiyithu/NerfingMVS.git
  

• Install python packages with anaconda. (modified)

  conda create -n NerfingMVS python=3.7
  conda activate NerfingMVS
  conda install pytorch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2 -c pytorch
  conda config --add channels conda-forge
  conda install imageio imageio-ffmpeg configargparse imagemagick
  pip install -r requirements.txt
  

• Add docker in /docker.

• We use COLMAP to calculate poses and sparse depths. However, original COLMAP does not have fusion mask for each view. Thus, we add masks to COLMAP and denote it as a submodule. Please follow https://colmap.github.io/install.html to install COLMAP in ./colmap folder (Note that do not cover colmap folder with the original version).