Access to large, diverse RGB-D datasets is critical for training RGB-D scene understanding algorithms. However, existing datasets still cover only a limited number of views or a restricted scale of spaces. In this paper, we introduce Matterport3D, a large-scale RGB-D dataset containing 10,800 panoramic views from 194,400 RGB-D images of 90 building-scale scenes. Annotations are provided with surface reconstructions, camera poses, and 2D and 3D semantic segmentations. The precise global alignment and comprehensive, diverse panoramic set of views over entire buildings enable a variety of supervised and self-supervised computer vision tasks, including keypoint matching, view overlap prediction, normal prediction from color, semantic segmentation, and region classification.

@inproceedings{Chang:2017:MLF,
   author = "Angel Chang and Angela Dai and Thomas Funkhouser and Maciej Halber and
      Matthias Nie{\ss}ner and Manolis Savva and Shuran Song and Andy
      Zeng and Yinda Zhang",
   title = "{Matterport3D}: Learning from {RGB-D} Data in Indoor Environments",
   booktitle = "IEEE International Conference on 3D Vision (3DV)",
   year = "2017",
   month = oct
}