论文标题
学习弱监督的3D实例细分的索佩波点亲和力
Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation
论文作者
论文摘要
由于3D点云的少数注释标签，如何学习点云的区分特征到细分对象实例是一个具有挑战性的问题。在本文中，我们提出了一个简单而有效的3D实例分割框架，该框架可以通过仅注释每个实例来实现良好的性能。具体而言，要解决极少的标签（例如分段），我们首先以无监督的方式将点云缩小到超级点，并将点级注释扩展到超级点级别。然后，基于SuperPoint图，我们提出了一个超级点的亲和力挖掘模块，该模块考虑语义和空间关系以适应性地学习superpoint的亲和力，以通过语义意识到的随机步行生成高质量的伪标签。最后，我们通过在SuperPoint Graph上的群集中应用对象限制来提出一个音量感知实例改进模块，以将对象的音量限制应用于分段高质量实例。 Scannet-V2和S3DIS数据集的大量实验表明，我们的方法在弱监督的点云实例分段任务中实现了最新的性能，甚至超过了一些完全监督的方法。
Due to the few annotated labels of 3D point clouds, how to learn discriminative features of point clouds to segment object instances is a challenging problem. In this paper, we propose a simple yet effective 3D instance segmentation framework that can achieve good performance by annotating only one point for each instance. Specifically, to tackle extremely few labels for instance segmentation, we first oversegment the point cloud into superpoints in an unsupervised manner and extend the point-level annotations to the superpoint level. Then, based on the superpoint graph, we propose an inter-superpoint affinity mining module that considers the semantic and spatial relations to adaptively learn inter-superpoint affinity to generate high-quality pseudo labels via semantic-aware random walk. Finally, we propose a volume-aware instance refinement module to segment high-quality instances by applying volume constraints of objects in clustering on the superpoint graph. Extensive experiments on the ScanNet-v2 and S3DIS datasets demonstrate that our method achieves state-of-the-art performance in the weakly supervised point cloud instance segmentation task, and even outperforms some fully supervised methods.
