A Point-Based Approach to Efficient LiDAR Multi-Task Perception

arXiv:2404.12798v1 Announce Type: new
Abstract: Multi-task networks can potentially improve performance and computational efficiency compared to single-task networks, facilitating online deployment. However, current multi-task architectures in point cloud perception combine multiple task-specific point cloud representations, each requiring a separate feature encoder and making the network structures bulky and slow. We propose PAttFormer, an efficient multi-task architecture for joint semantic segmentation and object detection in point clouds that only relies on a point-based representation. The network builds on transformer-based feature encoders …

abstract architectures arxiv cloud computational cs.cv current deployment efficiency encoder feature however lidar making multiple network networks perception performance type