无需人工标注，通过伪标签实现激光雷达中物体的无监督在线分割与跟踪。
UNIT: Unsupervised Online Instance Segmentation through Time
- 基于实例分割主干网络，设计新训练方法实现在线追踪。
- 在两个室外激光雷达数据集上优于强基线模型。
- 适用于自动驾驶等需实时理解环境的场景。
激光雷达点云中的在线目标分割与跟踪使自主智能体能够理解周围环境并做出安全决策。然而，这些任务的人工标注成本极高。本文提出一种无类别、无监督的在线实例分割与跟踪方法。我们利用实例分割主干网络，并提出一种新的训练方案，实现对移动物体的在线追踪。网络在伪标签上进行训练，无需人工标注。我们采用针对时序实例分割设计的评估指标，计算这些指标需要时间一致的实例标签；当标签不可用时，我们利用数据集中已有的3D边界框和语义标签构建这些标签。我们在两个不同的室外激光雷达数据集上进行了评估，并与多个强基线方法对比，证明了该方法的优越性。
原文摘要 · Abstract (English)
Online object segmentation and tracking in Lidar point clouds enables autonomous agents to understand their surroundings and make safe decisions. Unfortunately, manual annotations for these tasks are prohibitively costly. We tackle this problem with the task of class-agnostic unsupervised online instance segmentation and tracking. To that end, we leverage an instance segmentation backbone and propose a new training recipe that enables the online tracking of objects. Our network is trained on pseudo-labels, eliminating the need for manual annotations. We conduct an evaluation using metrics adapted for temporal instance segmentation. Computing these metrics requires temporally-consistent instance labels. When unavailable, we construct these labels using the available 3D bounding boxes and semantic labels in the dataset. We compare our method against strong baselines and demonstrate its superiority across two different outdoor Lidar datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。