通过通道关系与邻域一致性约束，提升点云特征聚合精度。
Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysis
- 引入通道级关系与邻域同质性约束，优化特征加权机制。
- 在S3DIS上达77.5% mIoU，ScanObjectNN上90.4% OA，性能领先。
- 轻量高效，可解释性强，适合点云理解与自动驾驶场景。
在三维点云理解中，准确捕捉复杂邻域内的判别性特征是核心挑战，直接影响具身智能与自动驾驶等下游任务的执行精度。现有方法虽探索特征相关性判别，但仅限于点级空间分布或通道响应，评估粒度粗，导致深层网络信息丢失严重。为此，我们提出PointCRA，一种基于通道级度量增强的新型网络。核心思想是引入时序趋势变化作为新评估维度，避免传统空间与通道注意力中权重维坍塌带来的信息损失。在此基础上，构建以邻域同质性为导向的多层级校准框架，并设计专用损失函数以增强通道判别力。PointCRA利用内在特征先验自适应修正特征聚合，兼具可解释性与低参数开销。我们在多个数据集和基准模型上验证该方法，并通过大量分析实验证明其合理性。在S3DIS上取得77.5% mIoU，ScanObjectNN上90.4% OA，ShapeNetPart上87.4%实例mIoU。代码与预训练权重已开源：https://github.com/AGENT9717/PointCRA
原文摘要 · Abstract (English)
In 3D point cloud understanding, the core challenge lies in accurately capturing discriminative features within complex neighborhoods, which directly affects the execution precision of downstream tasks such as embodied AI and autonomous driving. Existing methods explore feature correlation discrimination but are limited to point-level spatial distribution or channel responses, enabling only coarse-grained level evaluation. For modern multi-scale point cloud networks, such coarse-grained metrics inevitably incur significant information loss in deeper layers. To address this, we propose PointCRA, a novel network with a channel-level metric-based enhancement mechanism. Our core idea is to introduce temporal trend variation as a new evaluation dimension to avoid the information loss caused by weight dimension collapse in existing spatial and channel attention mechanisms. On this basis, we construct a multi-level calibration framework guided by neighborhood homogeneity for weight calibration, and design a dedicated loss function to enhance channel discriminability.PointCRA leverages intrinsic feature priors to adaptively correct feature aggregation, offering interpretability with low parameter overhead. Our method is transferable, interpretable, and efficient. We validate the proposed method on diverse datasets and benchmark models, and further demonstrate its rationality through extensive analytical experiments. Our PointCRA achieves 77.5\% mIoU on the S3DIS dataset, 90.4\% OA on the ScanObjectNN dataset, and 87.4\% instance mIoU on the ShapeNetPart dataset. The code and pretrained weights are publicly available on GitHub: https://github.com/AGENT9717/PointCRA
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。