SemanticKITTI

Introduced by Behley et al. in SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences

SemanticKITTI is a large-scale outdoor-scene dataset for point cloud semantic segmentation. It is derived from the KITTI Vision Odometry Benchmark which it extends with dense point-wise annotations for the complete 360 field-of-view of the employed automotive LiDAR. The dataset consists of 22 sequences. Overall, the dataset provides 23201 point clouds for training and 20351 for testing.

Source: Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
3D Semantic Segmentation	SemanticKITTI	PTv3 + PPT
3D Semantic Scene Completion	SemanticKITTI	TALoS
Semi-Supervised Semantic Segmentation	SemanticKITTI	PLE
3D Semantic Scene Completion from a single RGB image	SemanticKITTI	CGFormer
4D Panoptic Segmentation	SemanticKITTI	Mask4Former
Real-Time 3D Semantic Segmentation	SemanticKITTI	3D-MiniNet-tiny
LIDAR Semantic Segmentation	SemanticKITTI	AF2S3Net
Panoptic Segmentation	SemanticKITTI	59.0
Weakly supervised Semantic Segmentation	SemanticKITTI	Ours
Generalized Zero-Shot Learning	SemanticKITTI	3DGenZ