论文标题
Panoster：激光点云的端到端全景分割
Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds
论文作者
论文摘要
PANOPTIC分割最近已经统一的语义和实例分段，以前是单独解决的，因此朝着建立更全面和高效的感知系统迈出了一步。在本文中，我们提出了Panoster，这是一种新颖的无panoptic分割方法，用于激光点云。与以前的方法依靠多个步骤将像素或点分组到对象中不同，Panoster提出了一个简化的框架，该框架结合了基于学习的聚类解决方案以识别实例。在推论时，这充当了类不足的分割，使Panoster可以快速，同时在准确性方面优于先前的方法。在没有任何后处理的情况下，Panoster在挑战性的Semantickitti基准测试中达到了最新的结果，并通过利用启发式技术进一步提高了其领先优势。此外，我们展示了如何灵活有效地应用我们的方法上的现有语义体系结构以提供泛型预测。
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.
