论文标题
多级3D零件实例分割的语义分割辅助实例融合
Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation
论文作者
论文摘要
从3D点云中识别3D零件实例对于3D结构和场景理解至关重要。几种基于学习的方法使用语义细分和实例中心预测作为培训任务，并且无法进一步利用形状语义和部分实例之间的固有关系。在本文中，我们提出了一种用于3D份实例分割的新方法。我们的方法将语义分割利用为融合非本地实例特征（例如中心预测），并以多种和跨层次的方式进一步增强融合方案。我们还提出了一个语义区域中心预测任务，以训练和利用预测结果来改善实例点的聚类。我们的方法的表现优于现有方法，其Partnet基准测试的细胞范围很大。我们还证明，我们的功能融合方案可以应用于其他现有方法，以提高其在室内场景实例细分任务中的性能。
Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further exploit the inherent relationship between shape semantics and part instances. In this paper, we present a new method for 3D part instance segmentation. Our method exploits semantic segmentation to fuse nonlocal instance features, such as center prediction, and further enhances the fusion scheme in a multi- and cross-level way. We also propose a semantic region center prediction task to train and leverage the prediction results to improve the clustering of instance points. Our method outperforms existing methods with a large-margin improvement in the PartNet benchmark. We also demonstrate that our feature fusion scheme can be applied to other existing methods to improve their performance in indoor scene instance segmentation tasks.
