Skip to content


Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?

Introduction Build Status

The Multi-View Environment, MVE, is an implementation of a complete end-to-end pipeline for image-based geometry reconstruction. It features Structure-from-Motion, Multi-View Stereo and Surface Reconstruction. Further, this is an effort to ease the work with multi-view datasets and to support the development of algorithms based on multiple views. MVE has been developed at the TU Darmstadt by Michael Goesele's research group, and is cucrently in maintenance mode, i.e., new features are rarely added.

This README covers compilation and basic information about the pipeline. For documentation, please refer to the Wiki pages on GitHub.

MVE is written in C++ and comes with a set of easy-to-use, cross-platform libraries. The code runs on Linux, MacOS X and (sometimes) Windows. MVE has minimal dependencies on external libraries; it depends on libpng, libjpeg and libtiff. A front-end QT-based application called UMVE is built on top of these libraries, for visualization of the datasets.

If you use our system and want to mention MVE in your publications, please cite the following paper:

MVE – A Multi-View Reconstruction EnvironmentPaper, 10MB
Simon Fuhrmann, Fabian Langguth and Michael Goesele
In: Proceedings of the Eurographics Workshop on Graphics and Cultural Heritage, Darmstadt, Germany, 2014.

Building MVE and UMVE

To download and build MVE, type:

$ git clone
$ cd mve
$ make -j8

To compile and run UMVE, the Qt user interface, type:

$ cd apps/umve/
$ qmake && make -j8
$ ./umve

System requirements to compile and run MVE or UVME are:

Windows and OS X: Please refer to the Wiki pages for instructions.

The Reconstruction Pipeline

The MVE reconstruction pipeline is composed of the following components:

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

The individual steps of the pipeline are available as command line applications in the mve/apps/ directory. Please refer to the MVE Users Guide for a more detailed description how to use these tools. Note that UMVE is merely an interface for scene inspection and does not support reconstruction.


See the LICENSE.txt file and the source file headers for more details.