Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Chengwei, Zhang, Xueyi, Lao, Mingrui, Jiang, Tao, Xu, Xinhao, Li, Wenjie, Zhang, Fubo, Chen, Longyong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.11932
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915448096817152
author Zhang, Chengwei
Zhang, Xueyi
Lao, Mingrui
Jiang, Tao
Xu, Xinhao
Li, Wenjie
Zhang, Fubo
Chen, Longyong
author_facet Zhang, Chengwei
Zhang, Xueyi
Lao, Mingrui
Jiang, Tao
Xu, Xinhao
Li, Wenjie
Zhang, Fubo
Chen, Longyong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11932
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Learning For Point Cloud Denoising: A Survey
Zhang, Chengwei
Zhang, Xueyi
Lao, Mingrui
Jiang, Tao
Xu, Xinhao
Li, Wenjie
Zhang, Fubo
Chen, Longyong
Computer Vision and Pattern Recognition
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.
title Deep Learning For Point Cloud Denoising: A Survey
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.11932