4D Panoptic Segmentation

4D Panoptic Segmentation is a computer vision task aimed at performing semantic classification and instance tracking on point cloud sequences. Its core objective is to predict the semantic category of each point and ensure that the same object instance is consistently assigned the same instance ID throughout the point cloud sequence. The performance of this task is evaluated using the LSTQ metric, and it has significant application value for real-time scene understanding in areas such as autonomous driving and robot navigation.