Panoptic Perception for Autonomous Driving: A Survey

Traditional methodologies in vehicular perception typically compartmentalize tasks such as object detection, instance segmentation, and semantic segmentation, addressing each in isolation. While these modular approaches yield valuable insights, they fall short of providing an integrated, holistic understanding of the multifaceted driving environment. This limitation underscores the necessity for panoptic perception, an approach designed to unify disparate perception tasks within a comprehensive framework. The concept of panoptic perception was first introduced in the YOLOP[104] in 2021, marking a significant advancement in autonomous driving. Before this, and continuing presently, numerous multi-task networks have been developed with similar objectives, striving to enhance environmental perception in autonomous driving by unifying various perception tasks within a single, cohesive framework.