arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.17877cs.CV
收藏

通过深度迁移学习推进3D点云理解:一项全面综述

Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Survey

VIT Bhopal University(VIT博帕尔大学);University of Dubai(迪拜大学);University of Medea(迈迪亚大学);University of Sharjah(沙迦大学);De Montfort University(德蒙福特大学);Qatar University(卡塔尔大学)

Shahab Saquib Sohail, Yassine Himeur, Hamza Kheddar, Abbes Amira, Fodil Fadli, Shadi Atalla, Abigail Copiaco, Wathiq Mansoor

AI总结:

本文全面综述了利用深度迁移学习(DTL)和领域适应(DA)技术解决3D点云理解中数据匮乏、域差距及计算成本高等问题的最新方法、应用与未来方向。

摘要:

3D点云(3DPC)的演进显著受益于深度学习(DL)的进步。然而,后者面临诸多问题,包括缺乏数据或标注数据、训练数据与测试数据之间存在显著差距,以及对高计算资源的需求。为此,深度迁移学习(DTL)通过利用从源数据/任务中获取的知识来训练目标数据/任务,从而降低依赖和成本,已被广泛研究。人们已经提出了许多DTL框架,用于对齐从同一场景的多次扫描中获取的点云。此外,作为DTL子集的领域适应(DA)已被改进,通过处理噪声和缺失点来提升点云数据的质量。最终,微调和DA方法证明了其在解决点云数据固有独特困难方面的有效性。本文首次对这一方面进行了回顾。它全面概述了使用DTL和领域适应(DA)理解3DPC的最新技术。因此,首先介绍了DTL的背景以及数据集和评估指标。本文引入了一个定义明确的分类法,并考虑了不同方面(如不同的知识迁移策略和性能)进行了详细比较。本文涵盖了各种应用,例如3DPC目标检测、语义标注、分割、分类、配准、下采样/上采样和去噪。此外,文章讨论了所提出框架的优势和局限性,指出了开放性挑战,并提出了潜在的研究方向。

英文摘要:

The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of deep learning (DL). However, the latter faces various issues, including the lack of data or annotated data, the existence of a significant gap between training data and test data, and the requirement for high computational resources. To that end, deep transfer learning (DTL), which decreases dependency and costs by utilizing knowledge gained from a source data/task in training a target data/task, has been widely investigated. Numerous DTL frameworks have been suggested for aligning point clouds obtained from several scans of the same scene. Additionally, DA, which is a subset of DTL, has been modified to enhance the point cloud data's quality by dealing with noise and missing points. Ultimately, fine-tuning and DA approaches have demonstrated their effectiveness in addressing the distinct difficulties inherent in point cloud data. This paper presents the first review shedding light on this aspect. it provides a comprehensive overview of the latest techniques for understanding 3DPC using DTL and domain adaptation (DA). Accordingly, DTL's background is first presented along with the datasets and evaluation metrics. A well-defined taxonomy is introduced, and detailed comparisons are presented, considering different aspects such as different knowledge transfer strategies, and performance. The paper covers various applications, such as 3DPC object detection, semantic labeling, segmentation, classification, registration, downsampling/upsampling, and denoising. Furthermore, the article discusses the advantages and limitations of the presented frameworks, identifies open challenges, and suggests potential research directions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑