This software (CMVS) takes the output of a structure-from-motion (SfM) software as input, then decomposes the input images into a set of image clusters of managable size. An MVS software can be used to process each cluster independently and in parallel, where the union of reconstructions from all the clusters should not miss any details that can be otherwise obtained from the whole image set. CMVS should be used in conjunction with an SfM software Bundler and an MVS software PMVS2 (PMVS version 2).
Hi,I ran the colmap and got the sfm result. include sparse point cloud,camera poses and images.
I used the colmap command-line convert it to cmvs format.
then I ran the cmvs.exe the i got center-00001.ply ....
it just has the camera pose. I don't think the output is right.
I think the cmvs's output should include cluster images and cluster points.am I right?
can someone tell what is right output format of the cmvs ?
CMVS is computer clusters that can be processed independently by pmvs2 (Point Cloud computation)
I would advise you to first try to use pmvs2, and if it is too slow or memory consuming use CVMS + PMVS
pmoulon
commented
4 years ago
Hi,I ran the colmap and got the sfm result. include sparse point cloud,camera poses and images. I used the colmap command-line convert it to cmvs format. then I ran the cmvs.exe the i got center-00001.ply ....
it just has the camera pose. I don't think the output is right. I think the cmvs's output should include cluster images and cluster points.am I right? can someone tell what is right output format of the cmvs ?