You're currently viewing an old version of this dataset. To see the current version, click here.

ScanNet

ScanNet is a richly annotated dataset for 3D reconstruction of indoor scenes, containing RGB images, groundtruth depths, camera poses, surface reconstructions, and instance-level semantic segmentations.

Data and Resources

Cite this as

Angela Dai, Angel X Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner (2024). Dataset: ScanNet. https://doi.org/10.57702/yv5yc1z0

DOI retrieved: November 25, 2024

Additional Info

Field Value
Created November 25, 2024
Last update November 25, 2024
Author Angela Dai
More Authors
Angel X Chang
Manolis Savva
Maciej Halber
Thomas Funkhouser
Matthias Nießner
Homepage http://www.scan-net.org/