系统梳理点云分类与分割的深度学习架构，解析核心方法与挑战
A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation
- 按骨干网络结构分类，归纳主流点云处理模型
- 对比多个基准数据集上的性能表现，揭示优劣差异
- 适合3D视觉研究者参考，尤其关注点云理解的算法设计
点云因其简洁性和几何保真度，成为表示三维形状与场景最广泛使用的格式。然而，其固有的无序性和不规则性，加之传感器噪声和遮挡问题，给基于机器学习的方法带来了独特挑战。为应对这些问题，研究者提出了多种策略，包括将点云转换为有序格式、提取局部几何特征，以及采用排列不变或自注意力机制进行处理。本文聚焦于三维视觉中的三个基础任务：点云分类、部件分割和语义分割。首先形式化定义点云数据，并深入讨论其结构特性；随后根据骨干网络结构对代表性工作进行分类，并在主流基准上评估其性能。除了实证比较，还分析了架构创新与局限性，并展望了点云理解领域的开放挑战与未来方向。
原文摘要 · Abstract (English)
Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions, introduces unique challenges for machine learning based methodologies. To combat these issues, diverse strategies have been developed, including converting to a format that has orderliness, extracting local geometry, and permutation-invariant or self-attention-based processing. In this paper, our focus is directed towards deep learning models for three fundamental tasks in 3D vision: point cloud classification, part segmentation, and semantic segmentation. We begin by formally defining point cloud data, followed by an in-depth discussion on its structural characteristics. Then, we categorize notable works based on their backbone structure and evaluate their performance on popular benchmarks. Beyond empirical comparison, we offer insights into architectural innovations and limitations. We also outline open challenges and promising future directions for 3D point cloud understanding.
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。