SAGE3D通过引导注意力与图激励提升点云角点检测精度与召回率。
SAGE3D: Soft-guided attention and graph excitation for 3D point cloud corner detection
- 引入软引导注意力，用真值标签增强注意力权重以提高精度。
- 设计激发式图网络，在多尺度下仅正向传播强化高置信角点预测。
- 适用于航拍激光雷达点云的角点检测，尤其适合需高召回场景。
我们提出 SAGE3D，一种基于 Transformer 的混合模型，用于机载 LiDAR 点云中的角点检测。该方法基于分层编码器-解码器架构，通过 Set Abstraction 层逐步下采样点云，并利用 Feature Propagation 恢复逐点预测。提出两项创新：软引导注意力（Soft-Guided Attention），在训练中将真值角点标签作为对数先验注入注意力逻辑，提升检测精度；以及位于层次结构关键分辨率处的激发式图神经网络（Excitatory Graph Neural Network），采用仅正向消息传递机制，使高置信角点通过学习到的增强策略强化预测，优化召回率。分层设计支持多尺度特征提取，而引导注意力与激发模块确保角点信号在跨尺度过程中被放大而非稀释。
原文摘要 · Abstract (English)
We present SAGE3D, a hybrid Transformer-based model for corner detection in airborne LiDAR point clouds. We propose a multi-stage solution built on a hierarchical encoder-decoder architecture that progressively downsamples point clouds through Set Abstraction layers and recovers per-point predictions via Feature Propagation. We introduce two innovations: Soft-Guided Attention, which injects ground-truth corner labels as a log-prior into attention logits during training to improve precision; then an Excitatory Graph Neural Network positioned at strategic resolutions in the hierarchy, employing positive-only message passing where high-confidence corners reinforce predictions through learned boosting, optimizing for recall. The hierarchical design enables multi-scale feature extraction while our guided attention and excitatory modules ensure corner signals are amplified rather than diluted across scales.
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。