[论文解读] Decoupled Local Aggregation for Point Cloud Learning

Binjie Chen, Yunzhou Xia+3 more|arXiv (Cornell University)|Aug 31, 2023

3D Surveying and Cultural Heritage被引用 12

一句话总结

论文提出 DeLA，一种轻量化的解耦局部聚合框架，用于点云，通过在特征中编码空间信息并采用带边缘最大池化的简单池化，在降低延迟的同时达到最先进的结果。

ABSTRACT

The unstructured nature of point clouds demands that local aggregation be adaptive to different local structures. Previous methods meet this by explicitly embedding spatial relations into each aggregation process. Although this coupled approach has been shown effective in generating clear semantics, aggregation can be greatly slowed down due to repeated relation learning and redundant computation to mix directional and point features. In this work, we propose to decouple the explicit modelling of spatial relations from local aggregation. We theoretically prove that basic neighbor pooling operations can too function without loss of clarity in feature fusion, so long as essential spatial information has been encoded in point features. As an instantiation of decoupled local aggregation, we present DeLA, a lightweight point network, where in each learning stage relative spatial encodings are first formed, and only pointwise convolutions plus edge max-pooling are used for local aggregation then. Further, a regularization term is employed to reduce potential ambiguity through the prediction of relative coordinates. Conceptually simple though, experimental results on five classic benchmarks demonstrate that DeLA achieves state-of-the-art performance with reduced or comparable latency. Specifically, DeLA achieves over 90\% overall accuracy on ScanObjectNN and 74\% mIoU on S3DIS Area 5. Our code is available at https://github.com/Matrix-ASC/DeLA .

研究动机与目标

• 通过将空间关系学习与聚合解耦，减少局部聚合的复杂性。
• 提出空间编码，在不在每一步学习关系的情况下保留局部空间信息。
• 构建 DeLA 作为一个使用交错的逐点运算和边缘池化的轻量级网络。
• 引入正则化项以促进对空间编码的利用并降低歧义。
• 在分类和分割任务的标准点云基准上展示出强劲的性能。

提出的方法

• 定义空间编码，以从编码后的点特征在局部恢复相对坐标。
• 将标准局部聚合分解为基于集合嵌入的消息传递，涉及 g、M、h（Equation 7）。
• 将 DeLA 实例化为 Local Feature Propagation (LFP) 和边缘最大池化用于聚合。
• 通过一个小型 PointNet 处理每个阶段的邻域关系来形成空间编码。
• 使用 FPS 或网格下采样进行下采样，并利用跳跃连接保留源特征。
• 应用一个正则化项，用于预测相邻点之间的相对坐标，并在训练过程中逐步衰减该项。

实验结果

研究问题

• RQ1 将显式空间关系学习从局部聚合中解耦，是否能够维持或提高点云中特征融合的清晰度？
• RQ2 将空间信息嵌入点特征是否使得基本池化也能达到具有竞争力或更优的性能？
• RQ3 不同的空间编码和聚合算子对分割与分类任务有何影响？
• RQ4 在常用基准测试中，DeLA 在准确性和效率方面与最先进的方法相比如何？

主要发现

• DeLA 在各基准上实现了与最先进方法相当或更低延迟的性能。
• On S3DIS Area 5, DeLA attains OA 92.2, mAcc 80.0, mIoU 74.1, with throughput 468 instances/sec.
• On ScanNet v2, DeLA achieves the best validation mIoU among reported methods with a compact parameter count (8.0M).
• On ShapeNetPart, DeLA reaches ins. mIoU 87.0 and cat. mIoU 85.8 without voting, closely rivaling or surpassing many methods.
• On ScanObjectNN and ModelNet40, DeLA achieves OA 90.4 and 94.0 respectively with competitive mAcc 89.3 and 92.2.
• The ablations show relative spatial encoding (especially rel-first and rel-rest) is effective, and edge max-pooling provides robust aggregation.