Panoster: End-to-End Panoptic Segmentation of LiDAR Point Clouds

Panoptic segmentation has recently unified semantic and instance segmentation, previously addressed separately, thus taking a step further towards creating more comprehensive efficient perception systems. In this letter, we present Panoster, novel proposal-free panoptic method for LiDAR point clouds. Unlike previous approaches relying on several steps to group pixels or points into objects, Panoster proposes simplified framework incorporating learning-based clustering solution identify instances. At inference time, acts as class-agnostic allowing be fast, while outperforming prior methods in terms of accuracy. Without any post-processing, reached state-of-the-art results among published the challenging SemanticKITTI benchmark, increased its lead by exploiting heuristic techniques. Additionally, showcase how our can flexibly effectively applied diverse existing architectures deliver predictions.