SUNCG is an ongoing effort to establish a richly-annotated, large-scale dataset of 3D scenes. The dataset contains over 45K different scenes with manually created realistic room and furniture layouts. All of the scenes are semantically annotated at the object level. This website provides
  • Some basic statistics of the dataset.
  • A C++ toolbox for loading and viewing the data.
  • An online scene query GUI for exploring the dataset.
  • If you are a researcher and would like to get access to the data, please agree to the terms of use by filling out this form. After you agree, you will receive a link to a download script. If you have any questions please email us at suncgteam@googlegroups.com.


  • Dataset download python script available (register through form to get access). Jul 11th 2018
  • Initial data and toolbox release. Jan 1st 2017
  • Version Changelog

  • Changelog file describing SUNCG dataset versions is available here
  • Bibtex

        title= {Semantic Scene Completion from a Single Depth Image},
        author= {Song, Shuran and Yu, Fisher and Zeng, Andy and Chang, Angel X and Savva, Manolis and Funkhouser, Thomas},
        journal={IEEE Conference on Computer Vision and Pattern Recognition},

    Simulation Environments support SUNCG

    House3D: A Rich and Realistic 3D Environment
    Yi Wu, Yuxin Wu, Georgia Gkioxari and Yuandong Tian

    MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
    Manolis Savva, Angel X. Chang, Alexey Dosovitskiy, Thomas Funkhouser and Vladlen Koltun

    HoME: a Household Multimodal Environment
    Simon Brodeur, Ethan Perez, Ankesh Anand, Florian Golemo, Luca Celotti, Florian Strub, Jean Rouat, Hugo Larochelle, Aaron Courville