Deep learning for scene flow estimation on point clouds: a survey and prospective trends

Aiming at obtaining structural information and 3D motion of dynamic scenes, scene flow estimation has been an interest of research in computer vision and computer graphics for a long time. It is also a fundamental task for various applications such as autonomous driving. Compared to previous methods...

Full description

Saved in:
Bibliographic Details
Main Authors: Li, Zhiqi, Xiang, Nan, Chen, Honghua, Zhang, Jianjun, Yang, Xiaosong
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/10356/172211
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-172211
record_format dspace
spelling sg-ntu-dr.10356-1722112023-12-01T15:36:03Z Deep learning for scene flow estimation on point clouds: a survey and prospective trends Li, Zhiqi Xiang, Nan Chen, Honghua Zhang, Jianjun Yang, Xiaosong School of Computer Science and Engineering Engineering::Computer science and engineering 3D Scene Flow Literature Survey Aiming at obtaining structural information and 3D motion of dynamic scenes, scene flow estimation has been an interest of research in computer vision and computer graphics for a long time. It is also a fundamental task for various applications such as autonomous driving. Compared to previous methods that utilize image representations, many recent researches build upon the power of deep analysis and focus on point clouds representation to conduct 3D flow estimation. This paper comprehensively reviews the pioneering literature in scene flow estimation based on point clouds. Meanwhile, it delves into detail in learning paradigms and presents insightful comparisons between the state-of-the-art methods using deep learning for scene flow estimation. Furthermore, this paper investigates various higher-level scene understanding tasks, including object tracking, motion segmentation, etc. and concludes with an overview of foreseeable research trends for scene flow estimation. Published version 2023-11-29T05:43:29Z 2023-11-29T05:43:29Z 2023 Journal Article Li, Z., Xiang, N., Chen, H., Zhang, J. & Yang, X. (2023). Deep learning for scene flow estimation on point clouds: a survey and prospective trends. Computer Graphics Forum, 42(6), e14795-. https://dx.doi.org/10.1111/cgf.14795 0167-7055 https://hdl.handle.net/10356/172211 10.1111/cgf.14795 2-s2.0-85152089081 6 42 e14795 en Computer Graphics Forum © 2023 The Authors. Computer Graphics Forum published by Eurographics - The European Association for Computer Graphics and John Wiley & Sons Ltd. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
3D Scene Flow
Literature Survey
spellingShingle Engineering::Computer science and engineering
3D Scene Flow
Literature Survey
Li, Zhiqi
Xiang, Nan
Chen, Honghua
Zhang, Jianjun
Yang, Xiaosong
Deep learning for scene flow estimation on point clouds: a survey and prospective trends
description Aiming at obtaining structural information and 3D motion of dynamic scenes, scene flow estimation has been an interest of research in computer vision and computer graphics for a long time. It is also a fundamental task for various applications such as autonomous driving. Compared to previous methods that utilize image representations, many recent researches build upon the power of deep analysis and focus on point clouds representation to conduct 3D flow estimation. This paper comprehensively reviews the pioneering literature in scene flow estimation based on point clouds. Meanwhile, it delves into detail in learning paradigms and presents insightful comparisons between the state-of-the-art methods using deep learning for scene flow estimation. Furthermore, this paper investigates various higher-level scene understanding tasks, including object tracking, motion segmentation, etc. and concludes with an overview of foreseeable research trends for scene flow estimation.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Li, Zhiqi
Xiang, Nan
Chen, Honghua
Zhang, Jianjun
Yang, Xiaosong
format Article
author Li, Zhiqi
Xiang, Nan
Chen, Honghua
Zhang, Jianjun
Yang, Xiaosong
author_sort Li, Zhiqi
title Deep learning for scene flow estimation on point clouds: a survey and prospective trends
title_short Deep learning for scene flow estimation on point clouds: a survey and prospective trends
title_full Deep learning for scene flow estimation on point clouds: a survey and prospective trends
title_fullStr Deep learning for scene flow estimation on point clouds: a survey and prospective trends
title_full_unstemmed Deep learning for scene flow estimation on point clouds: a survey and prospective trends
title_sort deep learning for scene flow estimation on point clouds: a survey and prospective trends
publishDate 2023
url https://hdl.handle.net/10356/172211
_version_ 1784855605686566912