Skip to main content

Matterport3D: Learning from RGB-D Data in Indoor Environments

Author(s): Chang, Angel; Dai, Angela; Funkhouser, Thomas; Halber, Maciej; Niebner, Matthias; et al

To refer to this page use:
Abstract: 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.
Publication Date: 2017
Citation: Chang, Angel, Angela Dai, Thomas Funkhouser, Maciej Halber, Matthias Niebner, Manolis Savva, Shuran Song, Andy Zeng, and Yinda Zhang. "Matterport3D: Learning from RGB-D Data in Indoor Environments." In International Conference on 3D Vision (3DV) (2017): pp. 667-676. doi:10.1109/3DV.2017.00081
DOI: 10.1109/3DV.2017.00081
EISSN: 2475-7888
Pages: 667 - 676
Type of Material: Conference Article
Journal/Proceeding Title: International Conference on 3D Vision (3DV)
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.