Awesome Open Source
Awesome Open Source


MVStudio is a lightweight, easy to use, and integrated SfM (Structure from Motion) and MVS (Multi-View Stereo) solution. It is intended for learning/researching 3D computer vision.

Pre-built Binaries

Prebuilt executables (for macOS, Linux, and Windows) can be downloaded here.

Build from Source

MVStudio depends on some third-party libraries and all dependencies (except for Qt) are included in the distribution. To build MVStudio, you need Qt, CMake, and of course, a compiler:

MVStudio has been tested on macOS (Xcode >= 8), Windows (MSVC >=2015), and Linux (GCC >= 4.8, Clang >= 3.3). Machines nowadays typically provide higher supports, so you should be able to build MVStudio on almost all platforms.

There are many options to build MVStudio. Choose one of the following (or whatever you are familiar with):

  • Option 1: Use any IDE that can directly handle CMakeLists files to open the CMakeLists.txt in the root directory of MVStudio. Then you should have obtained a usable project and just build. I recommend using CLion or QtCreator.
  • Option 2: Use CMake to generate project files for your IDE. Then load the project to your IDE and build.
  • Option 3: Use CMake to generate Makefiles and then make (on Linux/macOS) or nmake(on Windows with Microsoft Visual Studio). For example, on Linux or macOS, you can simply
    $ cd MVStudio
    $ mkdir Release
    $ cd Release
    $ cmake -DCMAKE_BUILD_TYPE=Release ..
    $ make

Don't have any experience with C/C++ programming? Have a look at How to build MVStudio step by step.

How to use MVStudio

  • Create a project

    • Goto menu File -> New Project, choose a folder, fill in the project name, and Save the project file. The folder you choose will contain all (intermediate) results after reconstruction.
    • Goto menu File -> Add Images, choose the folder containing the images. This can also be done by right-clicking the image panel (upper right corner of the program).
  • Reconstruction

    • Menu Runconstruct -> Image Matching
    • Menu Runconstruct -> Run Sparse (SfM) and wait to see the sparse point cloud.
    • Menu Runconstruct -> Run Dense (MVS) and wait to see the dense point cloud.


MVStudio is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 3 of the License or (at your option) any later version. The full text of the license can be found in the accompanying 'License' file.

Should you have any questions, comments, or suggestions, please contact me at [email protected]

Liangliang Nan

March 26, 2018

Copyright (C) 2014

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
c-plus-plus (18,401
computer-vision (1,241
point-cloud (136
computer-graphics (134
reconstruction (45
pointcloud (33
photogrammetry (20
structure-from-motion (20
sfm (15