S3DIS (Stanford 3D Indoor Scene Dataset (S3DIS))

Introduced by Armeni et al. in 3D Semantic Parsing of Large-Scale Indoor Spaces

The Stanford 3D Indoor Scene Dataset (S3DIS) dataset contains 6 large-scale indoor areas with 271 rooms. Each point in the scene point cloud is annotated with one of the 13 semantic categories.

Source: Grid-GCN for Fast and Scalable Point Cloud Learning

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Semantic Segmentation	S3DIS Area5	OmniVec
Semantic Segmentation	S3DIS	PTv3 + PPT
3D Instance Segmentation	S3DIS	OneFormer3D
3D Semantic Segmentation	S3DIS	OneFormer3D
3D Object Detection	S3DIS	Point-GCC+TR3D
Panoptic Segmentation	S3DIS Area5	SuperCluster
3D Open-Vocabulary Instance Segmentation	S3DIS	Open3DIS
Generalized Zero-Shot Learning	S3DIS	3DGenZ
Panoptic Segmentation	S3DIS	SuperCluster
Few-shot 3D Point Cloud Semantic Segmentation	S3DIS	attMPTI