ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
release_6usysxrhwbf5tnhdoy3zpmso7q
by
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas
Funkhouser, Matthias Nießner
2017
Abstract
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.
In text/plain
format
Archived Files and Locations
application/pdf 5.2 MB
file_o74lmnq2jrdz5jhg2tjflnfiqm
|
arxiv.org (repository) web.archive.org (webarchive) |
1702.04405v1
access all versions, variants, and formats of this works (eg, pre-prints)