Mask4Former: Mask Transformer for 4D Panoptic Segmentation

arXiv:2309.16133v2 Announce Type: replace
Abstract: Accurately perceiving and tracking instances over time is essential for the decision-making processes of autonomous agents interacting safely in dynamic environments. With this intention, we propose Mask4Former for the challenging task of 4D panoptic segmentation of LiDAR point clouds. Mask4Former is the first transformer-based approach unifying semantic instance segmentation and tracking of sparse and irregular sequences of 3D point clouds into a single joint model. Our model directly predicts semantic instances and their temporal associations …

abstract agents arxiv autonomous autonomous agents cs.cv decision dynamic environments instance instances lidar making panoptic segmentation processes segmentation semantic tracking transformer type