论文标题
仔细观察点云分析中的本地聚合操作员
A Closer Look at Local Aggregation Operators in Point Cloud Analysis
论文作者
论文摘要
点云处理的网络体系结构的最新进展主要是由本地聚合操作员的新设计驱动的。但是，由于每个解决方案中的总体网络体系结构和实现细节，因此未仔细研究这些运营商对网络性能的影响。同时，大多数运营商仅用于浅层建筑。在本文中，我们重新访问了代表性的本地聚合操作员，并使用相同的深层架构来研究其性能。我们的调查表明，尽管这些运营商的设计不同，但所有这些运营商在同一网络输入和功能数字下对网络性能做出了相似的贡献，并导致标准基准测试的最新准确性。这一发现刺激了我们重新考虑当地聚合操作员进行点云处理的复杂设计的必要性。为此，我们提出了一个没有可学习权重的简单本地聚合操作员，命名为“位置合并”（POSPOOL），该操作员的性能比现有复杂的运算符相似或稍微好一些。特别是，一个具有POSPOOL层的简单深度残差网络在所有基准上都取得了出色的性能，这表现优于挑战性的Partnet数据集上先前的最新方法（7.4 MIOU）。该代码可在https://github.com/zeliu98/closerlook3d上公开获取
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
