arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.01294cs.CVcs.LG
收藏

点云分析中的局部聚合算子

A Closer Look at Local Aggregation Operators in Point Cloud Analysis

University of Science and Technology of China(中国科学技术大学);Microsoft Research Asia(微软亚洲研究院)

Ze Liu, Han Hu, Yue Cao, Zheng Zhang, Xin Tong

摘要:

点云处理网络架构的最新进展主要是由新设计的局部聚合算子驱动的。然而,这些运营商对网络性能的影响并没有仔细研究,由于不同的整体网络架构和实施细节,在每个解决方案。同时,大多数算子只适用于浅层结构。在本文中,我们重新审视了代表性的本地聚合运营商,并使用相同的深度残差架构来研究它们的性能。我们的调查表明,尽管这些运营商的不同设计,所有这些运营商作出惊人的相似的贡献,在相同的网络输入和特征数的网络性能,并导致在标准基准的最先进的准确性。这一发现促使我们重新思考点云处理中局部聚集算子设计的必要性。为此,我们提出了一个简单的本地聚合运算符,没有可学习的权重,名为位置池(PosPool),它的性能类似于或略优于现有的复杂运算符。特别是,具有PosPool层的简单深度残差网络在所有基准测试中都取得了出色的性能,在具有挑战性的PartNet数据集上的性能远远优于以前的方法(7.4 mIoU)。该代码可在https://github.com/zeliu98/CloserLook3D上公开获取

英文摘要:

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

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。

↑