Matterport3D: Learning from RGB-D Data in Indoor Environments
Authors:
Preprint
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.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- Semantic Scene Completion from a Single Depth Image2017
- Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks2017
- Self-Supervised Visual Descriptor Learning for Dense CorrespondenceIEEE Robotics and Automation Letters, 2016
- Learning to Navigate the Energy Landscape2016
- Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images2016
- Understanding RealWorld Indoor Scenes with Synthetic Data2016
- Data-Driven 3D Primitives for Single Image Understanding2013
- Real-time 3D reconstruction at scale using voxel hashingACM Transactions on Graphics, 2013
- Interactive and anisotropic geometry processing using the screened Poisson equationACM Transactions on Graphics, 2011