开放世界中的激光雷达全景分割
Lidar Panoptic Segmentation in an Open World
AI总结：
研究开放世界激光雷达全景分割问题，提出类别无关的分层点聚类与二值分割分类方法，在已知与未知类别上均取得优异性能。
摘要：
解决激光雷达全景分割（LPS）对于自动驾驶汽车的安全部署至关重要。LPS旨在识别和分割激光雷达点云，以匹配预定义的语义类别词汇表，包括可数物体的thing类别（例如行人和车辆）以及无定形区域的stuff类别（例如植被和道路）。重要的是，LPS要求分割单独的thing实例（例如每一辆车）。当前的LPS方法做出了一个不切实际的假设，即在真实的开放世界中语义类别词汇表是固定的，但事实上，随着机器人遇到预定义类别词汇表中被视为未知的新类别实例，类别本体通常随时间演变。为了解决这一不切实际的假设，我们研究了开放世界中的LPS（LiPSOW）：我们在具有预定义语义类别词汇表的数据集上训练模型，并研究它们对更大数据集的泛化能力，在这些更大数据集中可能出现thing和stuff类别的新实例。这种实验设置得出了有趣的结论。虽然现有技术训练特定类别的实例分割方法，并在已知类别上获得了最先进的结果，但基于类别无关的自底向上分组的方法在初始类别词汇表之外的类别（即未知类别）上表现良好。不幸的是，这些方法在已知类别上的表现与完全数据驱动的方法并不相当。我们的工作提出了一种折中方案：我们进行类别无关的点聚类，以分层方式对输入点云进行过分割，随后进行二值点段分类，类似于Region Proposal Network [1]。我们通过计算点段加权层次树中的割来获得最终的点云分割，这与语义分类无关。值得注意的是，这种统一方法在已知和未知类别上都取得了强大的性能。
英文摘要：
Addressing Lidar Panoptic Segmentation (LPS ) is crucial for safe deployment of autonomous vehicles. LPS aims to recognize and segment lidar points w.r.t. a pre-defined vocabulary of semantic classes, including thing classes of countable objects (e.g., pedestrians and vehicles) and stuff classes of amorphous regions (e.g., vegetation and road). Importantly, LPS requires segmenting individual thing instances (e.g., every single vehicle). Current LPS methods make an unrealistic assumption that the semantic class vocabulary is fixed in the real open world, but in fact, class ontologies usually evolve over time as robots encounter instances of novel classes that are considered to be unknowns w.r.t. the pre-defined class vocabulary. To address this unrealistic assumption, we study LPS in the Open World (LiPSOW): we train models on a dataset with a pre-defined semantic class vocabulary and study their generalization to a larger dataset where novel instances of thing and stuff classes can appear. This experimental setting leads to interesting conclusions. While prior art train class-specific instance segmentation methods and obtain state-of-the-art results on known classes, methods based on class-agnostic bottom-up grouping perform favorably on classes outside of the initial class vocabulary (i.e., unknown classes). Unfortunately, these methods do not perform on-par with fully data-driven methods on known classes. Our work suggests a middle ground: we perform class-agnostic point clustering and over-segment the input cloud in a hierarchical fashion, followed by binary point segment classification, akin to Region Proposal Network [1]. We obtain the final point cloud segmentation by computing a cut in the weighted hierarchical tree of point segments, independently of semantic classification. Remarkably, this unified approach leads to strong performance on both known and unknown classes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
