系统梳理深度学习点云去噪方法，厘清技术脉络与未来方向。
Deep Learning For Point Cloud Denoising: A Survey
- 将去噪拆解为去噪点和表面修复两步，构建针对性分类体系。
- 对比分析现有方法在结构与性能上的异同，总结关键优势。
- 适合研究点云处理、3D视觉的学者快速掌握去噪技术全貌。
真实环境中获取的点云普遍存在多种模态与强度的噪声，因此点云去噪（PCD）作为预处理步骤对提升下游任务性能至关重要。基于深度学习（DL）的点云去噪方法因其强大的表征能力与灵活架构，已超越传统方法。然而，尽管性能持续进步，目前尚无系统性综述全面总结基于深度学习的点云去噪发展。本文旨在识别关键挑战，归纳现有方法的核心贡献，并提出专为去噪任务设计的分类体系。为此，我们将点云去噪建模为两个步骤：离群点移除与表面噪声恢复，覆盖多数实际场景与需求。同时，从相似性、差异性及各自优势出发比较不同方法。最后，探讨当前研究局限与未来方向，为该领域进一步发展提供洞见。
原文摘要 · Abstract (English)
Real-world environment-derived point clouds invariably exhibit noise across varying modalities and intensities. Hence, point cloud denoising (PCD) is essential as a preprocessing step to improve downstream task performance. Deep learning (DL)-based PCD models, known for their strong representation capabilities and flexible architectures, have surpassed traditional methods in denoising performance. To our best knowledge, despite recent advances in performance, no comprehensive survey systematically summarizes the developments of DL-based PCD. To fill the gap, this paper seeks to identify key challenges in DL-based PCD, summarizes the main contributions of existing methods, and proposes a taxonomy tailored to denoising tasks. To achieve this goal, we formulate PCD as a two-step process: outlier removal and surface noise restoration, encompassing most scenarios and requirements of PCD. Additionally, we compare methods in terms of similarities, differences, and respective advantages. Finally, we discuss research limitations and future directions, offering insights for further advancements in PCD.
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。