Matterport3D: Learning from RGB-D Data in Indoor Environments

TL;DR

Matterport3D is a large-scale, diverse RGB-D dataset with panoramic views and detailed annotations, designed to advance indoor scene understanding and support various computer vision tasks.

Contribution

The paper introduces Matterport3D, a comprehensive RGB-D dataset with extensive views, annotations, and global alignment for indoor scene understanding.

Findings

Enables training of scene understanding algorithms with diverse indoor data

Supports multiple vision tasks including segmentation and keypoint matching

Provides precise global alignment and panoramic views

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.