SemanticKITTI

홈페이지 · 논문 669편

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 Image Source: https://github.com/PRBonn/semantic-kitti-api

LiDAR

벤치마크

3D Semantic Segmentation on SemanticKITTI 결과 136개

3D Semantic Scene Completion on SemanticKITTI 결과 62개

3D Semantic Scene Completion from a single RGB image on SemanticKITTI 결과 54개

Semi-Supervised Semantic Segmentation on SemanticKITTI 결과 24개

Real-Time 3D Semantic Segmentation on SemanticKITTI 결과 12개

4D Panoptic Segmentation on SemanticKITTI 결과 7개

Panoptic Segmentation on SemanticKITTI 결과 6개

LIDAR Semantic Segmentation on SemanticKITTI 결과 5개

Lidar Scene Completion on SemanticKITTI 결과 5개

Generalized Zero-Shot Learning on SemanticKITTI 결과 1개