Semantic segmentation of 3D point clouds relies on training deep models with a large amount of labeled data. However, labeling 3D point clouds is expensive, thus smart approach towards data annotation, a.k.a. active learning is essential to label-efficient point cloud segmentation. In this work, we first propose a more realistic annotation counting scheme so that a fair benchmark is possible. To better exploit labeling budget, we adopt a super-point based active learning strategy where we make use of manifold defined on the point cloud geometry. We further propose active learning strategy to encourage shape level diversity and local spatial consistency constraint. Experiments on two benchmark datasets demonstrate the efficacy of our proposed active learning strategy for label-efficient semantic segmentation of point clouds. Notably, we achieve significant improvement at all levels of annotation budgets and outperform the state-of-the-art methods under the same level of annotation cost.
翻译:3D点云的语义分解取决于对含有大量标签数据的深度模型的培训。 但是, 标为 3D点云的成本昂贵, 从而对数据注释( a.k.a.a.) 采取明智的方法。 积极学习对于标签高效点云分解至关重要 。 在这项工作中, 我们首先提出一个更现实的批注计方案, 以便有可能有一个公平的基准。 为了更好地利用标签预算, 我们采取了基于超级点的积极学习战略, 利用点云几何法上定义的方块。 我们进一步提出积极的学习战略, 鼓励形状层次的多样性和地方空间一致性限制。 对两个基准数据集的实验显示了我们拟议的关于点云的标签高效语义分解的积极学习战略的功效。 值得注意的是, 我们在所有层次的批注预算上都取得了显著的改进, 并且超越了同一水平的批注成本下的最新方法。