• Jian Zhang, Kan Chen, Alexander G. Schwing, Raquel Urtasun

  • Dataset

    We provide the following dataset as an extention to the NYU depth V2:
    The dataset includes the index of 303 images we sampled from the original 1449 images, the index of training and test set samples in our sub-dataset consisting 303 images, the pixel-wise 5-class annotation of the room layout, and the pixel-wise 6-class (including clutter) segmentation ground truth.

  • Download dataset of the 303 images we sampled from the original 1449 images.
  • Please see ReadMe for detailed specification of the above data.

  • Code and Data

    We provide the code and data used for inference and visualization in our project:
  • code and data for inference and visualization of estimated results.
  • Please see ReadMe for detailed description of the above code.

  • Contact

    For questions regarding the data please contact Jian Zhang.


    The data was developed as part of the following publication:
  • Estimating the 3D Layout of Indoor Scenes and Its Clutter from Depth Sensors
    J. Zhang, K. Chen, A. G. Schwing, R. Urtasun.
    International Conference on Computer Vision (ICCV), Sydney, Australia, December 2013.