With advances in data collection technology, the volume of recent remote sensing point cloud datasets has grown significantly, posing substantial challenges for point cloud deep learning, particularly in neighborhood aggregation operations. Unlike simple pooling, neighborhood aggregation incorporates spatial relationships between points into the feature aggregation process, requiring repeated relationship learning and resulting in substantial computational redundancy. The exponential increase in data volume exacerbates this issue. To address this, we theoretically demonstrate that if basic spatial information is encoded in point features, simple pooling operations can effectively aggregate features. This means the spatial relationships can be extracted and integrated with other features during aggregation. Based on this concept, we propose a lightweight point network called DeLA (Decoupled Local Aggregation). DeLA separates the traditional neighborhood aggregation process into distinct spatial encoding and local aggregation operations, reducing the computational complexity by a factor of K, where K is the number of neighbors in the K-Nearest Neighbor algorithm (K-NN). Experimental results on five classic benchmarks show that DeLA achieves state-of-the-art performance with reduced or equivalent latency. Specifically, DeLA exceeds 90% overall accuracy on ScanObjectNN and 74% mIoU on S3DIS Area 5. Additionally, DeLA achieves state-of-the-art results on ScanNetV2 with only 20% of the parameters of equivalent models. Our code is available at https://github.com/Matrix-ASC/DeLA.

中文翻译：

---

DeLA：一个速度极快的网络，具有解耦的本地聚合，适用于大规模点云学习


随着数据收集技术的进步，最近的遥感点云数据集的数量显著增长，对点云深度学习提出了重大挑战，尤其是在邻域聚合操作中。与简单的池化不同，邻域聚合将点之间的空间关系合并到特征聚合过程中，这需要重复的关系学习并导致大量的计算冗余。数据量的指数级增长加剧了这个问题。为了解决这个问题，我们从理论上证明，如果基本空间信息编码在点特征中，简单的池化操作可以有效地聚合特征。这意味着在聚合期间可以提取空间关系并将其与其他要素集成。基于这个概念，我们提出了一种称为 DeLA （Decoupled Local Aggregation） 的轻量级点网络。DeLA 将传统的邻域聚合过程分为不同的空间编码和局部聚合操作，将计算复杂性降低了 K 倍，其中 K 是 K 最近邻算法 （K-NN） 中的邻域数。五项经典基准测试的实验结果表明，DeLA 实现了最先进的性能，同时降低或等效了延迟。具体来说，DeLA 在 ScanObjectNN 上超过 90% 的总体准确率，在 S3DIS Area 5 上超过 74% 的 mIoU。此外，DeLA 在 ScanNetV2 上实现了最先进的结果，参数仅为等效模型的 20%。我们的代码可在 https://github.com/Matrix-ASC/DeLA 获取。