点云上的群内关系学习
Learning Inner-Group Relations on Point Clouds
摘要:
关系网络在计算机视觉中的流行与未充分探索的基于点的方法形成鲜明对比。在本文中,我们探讨了当地的关系运营商的可能性,并调查其可行性。我们提出了一个可扩展的和高效的模块,称为组关系聚合器。该模块基于由几何关系和语义关系加权的组内点的特征的聚合来计算组的特征。我们采用这个模块来设计我们的RPNet。我们进一步验证了RPNet的可扩展性,在深度和宽度方面,分类和分割的任务。令人惊讶的是,实证结果表明,更宽的RPNet适合分类,而更深的RPNet更适合分割。RPNet在具有挑战性的基准上实现了最先进的分类和分割。我们还将本地聚合器与PointNet++进行了比较,节省了大约30%的参数和50%的计算。最后,我们进行实验,以揭示RPNet的刚性变换和噪声的鲁棒性。
英文摘要:
The prevalence of relation networks in computer vision is in stark contrast to underexplored point-based methods. In this paper, we explore the possibilities of local relation operators and survey their feasibility. We propose a scalable and efficient module, called group relation aggregator. The module computes a feature of a group based on the aggregation of the features of the inner-group points weighted by geometric relations and semantic relations. We adopt this module to design our RPNet. We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation. Surprisingly, empirical results show that wider RPNet fits for classification, while deeper RPNet works better on segmentation. RPNet achieves state-of-the-art for classification and segmentation on challenging benchmarks. We also compare our local aggregator with PointNet++, with around 30% parameters and 50% computation saving. Finally, we conduct experiments to reveal the robustness of RPNet with regard to rigid transformation and noises.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。