paper-with-me

S3DIS

Stanford 3D Indoor Scene Dataset (S3DIS)

홈페이지 · 논문 488편

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 Image Source: https://www.researchgate.net/figure/Examples-of-classified-scenes-in-S3DIS-dataset-left-with-groundtruth-right_fig2_328307943

3DPoint cloud

벤치마크

Semantic Segmentation on S3DIS Area5 결과 122개

Semantic Segmentation on S3DIS 결과 110개

3D Instance Segmentation on S3DIS 결과 42개

3D Object Detection on S3DIS 결과 42개

3D Semantic Segmentation on S3DIS 결과 18개

Panoptic Segmentation on S3DIS Area5 결과 15개

3D Open-Vocabulary Instance Segmentation on S3DIS 결과 4개

Panoptic Segmentation on S3DIS 결과 3개

Generalized Zero-Shot Learning on S3DIS 결과 1개