ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
This provides a crucial resource for researchers in 3D computer vision, enabling supervised deep learning methods for indoor scene understanding, though it is incremental as it builds on existing dataset efforts.
The authors tackled the lack of large, labeled datasets for RGB-D scene understanding by introducing ScanNet, a dataset with 2.5M views in 1513 scenes annotated with 3D poses, reconstructions, and semantic segmentations, which helped achieve state-of-the-art performance on tasks like 3D object classification and semantic voxel labeling.
A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available -- current datasets cover a small range of scene views and have limited semantic annotations. To address this issue, we introduce ScanNet, an RGB-D video dataset containing 2.5M views in 1513 scenes annotated with 3D camera poses, surface reconstructions, and semantic segmentations. To collect this data, we designed an easy-to-use and scalable RGB-D capture system that includes automated surface reconstruction and crowdsourced semantic annotation. We show that using this data helps achieve state-of-the-art performance on several 3D scene understanding tasks, including 3D object classification, semantic voxel labeling, and CAD model retrieval. The dataset is freely available at http://www.scan-net.org.