Recent advances of network architecture for point cloud processing are mainly driven by new designs of local aggregation operators. However, the impact of these operators to network performance is not carefully investigated due to different overall network architecture and implementation details in each solution. Meanwhile, most of operators are only applied in shallow architectures. In this paper, we revisit the representative local aggregation operators and study their performance using the same deep residual architecture. Our investigation reveals that despite the different designs of these operators, all of these operators make surprisingly similar contributions to the network performance under the same network input and feature numbers and result in the state-of-the-art accuracy on standard benchmarks. This finding stimulate us to rethink the necessity of sophisticated design of local aggregation operator for point cloud processing. To this end, we propose a simple local aggregation operator without learnable weights, named Position Pooling (PosPool), which performs similarly or slightly better than existing sophisticated operators. In particular, a simple deep residual network with PosPool layers achieves outstanding performance on all benchmarks, which outperforms the previous state-of-the methods on the challenging PartNet datasets by a large margin (7.4 mIoU). The code is publicly available at https://github.com/zeliu98/CloserLook3D
翻译:点云处理网络架构的最近进展主要受本地集成操作员的新设计驱动。然而,由于每个解决方案中不同的整体网络架构和执行细节不同,这些操作员对网络性能的影响没有得到认真调查。同时,大多数操作员只应用在浅层结构中。在本文件中,我们重新审视具有代表性的本地集成操作员,并使用同样的深层残余结构研究其性能。我们的调查显示,尽管这些操作员的设计不同,但所有这些操作员都对同一网络输入和特征数字下的网络性能作出了惊人相似的贡献,并导致标准基准的精确度达到最新水平。这一发现促使我们重新思考对点云处理本地集成操作员的复杂设计的必要性。为此,我们提议建立一个简单的本地集成操作员,不具有可学习的重量,称为定位集合(Pospool),其性能与现有的精密操作员相似或略优于现有的操作员。特别是,一个与波斯波尔层的简单深度残余网络在所有基准上都取得了杰出的性能,这超过了以往在具有挑战性的部分网格的数据设置上采用的方法(7.4 mIULUS/DGUGUGU3) 公开提供的代码。 http。