OpenMVS (Multi-View Stereo) is a library for computer-vision scientists and especially targeted to the Multi-View Stereo reconstruction community. While there are mature and complete open-source projects targeting Structure-from-Motion pipelines (like OpenMVG) which recover camera poses and a sparse 3D point-cloud from an input set of images, there are none addressing the last part of the photogrammetry chain-flow. OpenMVS aims at filling that gap by providing a complete set of algorithms to recover the full surface of the scene to be reconstructed. The input is a set of camera poses plus the sparse point-cloud and the output is a textured mesh. The main topics covered by this project are:

• dense point-cloud reconstruction for obtaining a complete and accurate as possible point-cloud
• mesh reconstruction for estimating a mesh surface that explains the best the input point-cloud
• mesh refinement for recovering all fine details
• mesh texturing for computing a sharp and accurate texture to color the mesh

See the complete documentation on wiki.

See the building wiki page.

Continuous integration:

• linux 64 bits/GCC:

See the usage example wiki page.

See the copyright file.

openmvs[AT]googlegroups.com