重建步骤

  1. Creating a dataset, by converting the input photos into the MVE File Format.
  2. Structure from Motion, which reconstructs the camera parameters of the input photos.
  3. Multi-View Stereo, which reconstructs dense depth maps for each image.
  4. Surface Reconstruction, which reconstructs a surface mesh from the depth maps.

截屏2020-01-08上午10.46.49

http://www.cs.cmu.edu/~reconstruction/basic_workflow.html

使用方法

----------------Creating a Dataset------------------------------------------
$ makescene -i image-dir scene-dir
----------------Structure from Motion---------------------------------------
$ sfmrecon scene-dir
----------------Multi-View Stereo-------------------------------------------
$ dmrecon -s2 scene-dir
----------------Point Cloud Export------------------------------------------
$ scene2pset -F2 scene-dir scene-dir/pset-L2.ply
----------------Floating Scale Surface Reconstruction-----------------------
$ fssrecon scene-dir/pset-L2.ply scene-dir/surface-L2.ply
$ meshclean -t10 scene-dir/surface-L2.ply scene-dir/surface-L2-clean.ply

注：目前 UMVE 功能不完整，建议在终端实现重建过程。

参考文献