GigaVoxels / GigaSpace
              A CUDA/GLSL library for the efficient 3D real-time rendering of highly detailed scenes.

what is GigaVoxels


You can use GigaVoxel s renderer in GLSL but full GigaVoxels - especially the dynamics allocation, production and loading - is based on the Nvidia CUDA library. You will need a Nvidia graphics cards : at least a Fermi with a compute capability 2.0 and Cuda >= 7. GigaVoxels/GigaSpace is available on Windows (W7 or more) and Linux (Ubuntu 14 or more).


- Registration form.

Windows and Linux packages and archives:

- Go to download directory.

  • Windows: ( without the data required for demos )
        - Auto-installer with all the demos
        - DLL precompiled for Visual C++ 2013, 2012, 2010
        - Sources + external libs: (.zip)
        - Sources of externals: (.zip)

  • Linux: (Ubuntu 14.04) ( without the data required for demos )
        - Base package (.deb)
        - SDK package (.deb)
        - Demos package (.deb)
        - sources (.tgz)
        - Sources + external libs: (.zip)

  • All the data for the demos :
        - , to be unzipped and copied or merged into the GigaVoxels directory :
            - Windows : copy content to Program Files (x86)\GigaVoxels_v100\Data
            - Linux : use scripts in the install directory.

  • Via INRIA-forge and svn:

  • access to the Git on Gitlab.

    How to start

    Once you installed the data, either :
  • launch gigavoxels-viewer / GvViewer and load demos from the file menu (various tabs let you acces demo or GigaVoxels parameters)
  • or launch individual demoXXX.exe files from the prog directory.

  • NB: defaults values or side effects in GvViewer can be missleading.
    And some tutos differ by the programming approach more than by what you see.
    So, do have a look on the manual !


    GigaVoxels/Gigaspace distributed under the BSD 3 free software license, for non-commercial as well as commercial use.

    This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the BSD3 License for more details.

    As a research center INRIA cannot ensure long term software maintenance, but a community out of INRIA might help you on, and INRIA might be able to answer or redirect concerning special needs (e.g. development, formation). For both, see contact.


    GigaVoxels has been developped during the PhD thesis of Cyril Crassin (granted by the French Research Ministry via Grenoble University), under the advising of Fabrice Neyret (CNRS).

    GigaVoxels was supported and funded by ANR via the "veRTIGE" project (Real-Time Interactive & Galaxy for Edutainment) of reference ANR-10-CORD-0006

    Many other partial fundings and human participants have help or experimented directly or indirectly. Engineers (Morgan Armand, Pascal Guehl, Jeremy Sinoir, Paul Gannay), practice students, co-authors of the various papers, collegues in labs of companies with precious advices, and peoples from various INRIA support services... Thanks to all of them !