用局部点块构建3D边缘检测新方法，提升细节捕捉能力。
EdgeFormer: local patch-based edge detection transformer on point clouds
- 将全局点云转为局部点块，通过点分类实现边缘检测
- 在多个基准数据集上优于6个现有方法，边缘细节更清晰
- 适合需要高精度3D几何结构识别的工业应用
3D点云中的边缘点能清晰呈现三维几何与表面特征，因此边缘检测在众多视觉应用中具有广泛需求。然而，由于细粒度边缘特征通常密集分布或具有微小表面梯度，难以有效检测。为此，我们提出一种基于学习的边缘检测网络 EdgeFormer，包含两个阶段：首先基于空间邻近点具有高相关性、构成局部表面的观察，将整个点云的边缘检测转化为基于局部点块的点分类任务；第一阶段构建描述每个点周围局部邻域的局部点块特征描述符；第二阶段通过分析这些描述符对每个点进行分类。该方法将点云转换为局部点块后，能有效提取更精细的细节。实验结果表明，本模型在多个基准测试中表现优于六个基线方法。
原文摘要 · Abstract (English)
Edge points on 3D point clouds can clearly convey 3D geometry and surface characteristics, therefore, edge detection is widely used in many vision applications with high industrial and commercial demands. However, the fine-grained edge features are difficult to detect effectively as they are generally densely distributed or exhibit small-scale surface gradients. To address this issue, we present a learning-based edge detection network, named EdgeFormer, which mainly consists of two stages. Based on the observation that spatially neighboring points tend to exhibit high correlation, forming the local underlying surface, we convert the edge detection of the entire point cloud into a point classification based on local patches. Therefore, in the first stage, we construct local patch feature descriptors that describe the local neighborhood around each point. In the second stage, we classify each point by analyzing the local patch feature descriptors generated in the first stage. Due to the conversion of the point cloud into local patches, the proposed method can effectively extract the finer details. The experimental results show that our model demonstrates competitive performance compared to six baselines.
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。