ScanNet is an instance-level indoor RGB-D dataset that includes both 2D and 3D data. It is a collection of labeled voxels rather than points or objects. Up to now, ScanNet v2, the newest version of ScanNet, has collected 1513 annotated scans with an approximate 90% surface coverage. In the semantic segmentation task, this dataset is marked in 20 classes of annotated 3D voxelized objects.
Source: A Review of Point Cloud Semantic Segmentation
Image Source: http://www.scan-net.org/
Variants: ScanNet, ScanNetV1, ScanNetV2, ScanNet(v2)
This dataset is used in 7 benchmarks:
Recent papers with results on this dataset: