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).
Hey,
here's a set of fixes we carry locally that we'd like to upstream.
The key points are
.ply
filesFor the last point, it fixes expected output like this:
degenerating into output like this when the object is not close to the origin:
Close-up: