Capturing both local and global features of irregular point clouds is essential to 3D object detection (3OD). However, mainstream 3D detectors, e.g., VoteNet and its variants, either abandon considerable local features during pooling operations or ignore many global features in the whole scene context. This paper explores new modules to simultaneously learn local-global features of scene point clouds that serve 3OD positively. To this end, we propose an effective 3OD network via simultaneous local-global feature learning (dubbed 3DLG-Detector). 3DLG-Detector has two key contributions. First, it develops a Dynamic Points Interaction (DPI) module that preserves effective local features during pooling. Besides, DPI is detachable and can be incorporated into existing 3OD networks to boost their performance. Second, it develops a Global Context Aggregation module to aggregate multi-scale features from different layers of the encoder to achieve scene context-awareness. Our method shows improvements over thirteen competitors in terms of detection accuracy and robustness on both the SUN RGB-D and ScanNet datasets. Source code will be available upon publication.
翻译:然而,主流3D探测器,例如VoteNet及其变体,要么放弃相当的地方特征,要么在整个场景背景中忽略许多全球特征。本文探讨新的模块,同时学习对3OD有正面作用的场点云的局部和全球特征。为此,我们提议通过同时进行地方-全球特征学习(Dubbbbed 3DLG-探测器),建立一个有效的3OD网络。3DLG-探测器有两个关键贡献。首先,它开发了一个动态点互动(DPI)模块,在集合期间保存有效的当地特征。此外,新闻部可以分解,可以纳入现有的3OD网络,以提高其性能。第二,它开发了一个全球环境汇总模块,从编码的不同层收集多尺度特征,以实现对场景环境的认识。我们的方法显示在SUN RGB-D和扫描网络数据集的检测准确性和稳健度方面超过13个竞争者。源代码将在出版时公布。