Panoster: End-To-End Panoptic Segmentation Of Lidar Point Clouds
IEEE ROBOTICS AND AUTOMATION LETTERS(2021)
摘要
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 letter, 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.
更多查看译文
关键词
Computer vision for transportation, deep learning for visual perception, LiDAR point clouds, panoptic segmentation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络