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