Point Cloud Upsampling Algorithm: A Systematic Review

Zhang, Yan; Zhao, Wenhan; Sun, Binyong; Zhang, Ying; Wen, Wen

doi:10.3390/a15040124

Cited by 16 publications

(8 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[65], [66], [99], [100], [148], [149] Transformer [12], [54], [112], [150] [14], [29], [151]- [153] [50] Other [32], [113] [50]…”

Section: E Transformer-based Networkmentioning

confidence: 99%

“…Evaluation metrics that can measure the effect of noise and density distribution could be useful to analyse the completion results with respect to the inputs. Assistive Tasks and Feature Representation: During our survey, we found a few works that take assistance from other point clouds tasks such as segmentation [51], [98], [114], generation [167], upsampling [150], [208], classification [72], and object detection [7], [209]. Completion also benefits from the use of multitask point generation models [143], [145] and multitask feature learning [210].…”

Section: Future Workmentioning

confidence: 99%

See 1 more Smart Citation

Point Cloud Completion: A Survey

Tesema,

Hill,

Jones

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Point cloud completion is the task of producing a complete 3D shape given an input of a partial point cloud. It has become a vital process in 3D computer graphics, vision and applications such as autonomous driving, robotics, and augmented reality. These applications often rely on the presence of a complete 3D representation of the environment. Over the past few years, many completion algorithms have been proposed and a substantial amount of research has been carried out. However, there are not many in-depth surveys that summarise the research progress in such a way that allows users to make an informed choice of what algorithms to employ given the type of data they have, the end result they want, the challenges they may face and the possible strategies they could use. In this study, we present a comprehensive survey and classification of papers on point cloud completion untill August 2023 based on the strategies, techniques, inputs, outputs, and network architectures. We will also cover datasets, evaluation methods, and application areas in point cloud completion. Finally, we discuss challenges faced by the research community and future research directions.

show abstract

“…[65], [66], [99], [100], [148], [149] Transformer [12], [54], [112], [150] [14], [29], [151]- [153] [50] Other [32], [113] [50]…”

Section: E Transformer-based Networkmentioning

confidence: 99%

Section: Future Workmentioning

confidence: 99%

Point Cloud Completion: A Survey

Tesema,

Hill,

Jones

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…Dataset issues: Deep learning algorithms for point cloud upsampling lack benchmark datasets [16] , and creating point cloud upsampling datasets is challenging and costly. Researchers often face significant discrepancies when training network models with different datasets, hindering comparisons between point cloud upsampling algorithms and the advancement of subsequent related work.…”

Section: Pu-netmentioning

confidence: 99%

“…Evaluation metric issues: The evaluation metrics for point cloud upsampling algorithms mainly assess the quality of the upsampled point cloud based on the deviation between the true values and the generated point cloud, as well as the uniformity of the generated point cloud. Currently, there is no unified evaluation metric to measure the quality of deep learning algorithms for point cloud upsampling [16] . Future research should develop more scientific and objective quantitative assessment indicators to evaluate the performance and merits of point cloud upsampling methods.…”

Section: Pu-netmentioning

confidence: 99%

See 1 more Smart Citation

Research on deep learning algorithms for point cloud upsampling

Li,

Gong,

et al. 2023

Third International Conference on Digital Signal and Computer Communications (DSCC 2023)

View full text Add to dashboard Cite

The integration of 3D vision technology has profoundly impacted various aspects of our lives, with point clouds emerging as the predominant geometric representation in the field due to their simplicity, ease of processing, and low acquisition costs. However, limitations in 3D scanning hardware often result in sparse, noisy, and unevenly distributed point clouds, which impede the effectiveness of subsequent 3D vision tasks. To obtain high-quality and precise point clouds, researchers have introduced upsampling algorithms that enhance point cloud representativeness through densification.In recent years, deep learning has supplanted traditional algorithms that rely on a priori data, owing to its robust learning representation capabilities and data-driven nature. Consequently, deep learning algorithms for point cloud upsampling have become a highly valuable research direction within the 3D vision domain. This paper delves into recent advancements in deep learning algorithms for point cloud upsampling by first defining the problem and analyzing the technical challenges from six perspectives. It then provides an overview of the relevant benchmarks in point cloud upsampling and traces their developmental history.The paper further examines the technical issues in the three critical steps (point cloud local feature extraction, feature space expansion, and coordinate reconstruction) of the overall deep learning algorithm for point cloud upsampling. It categorizes the prevalent technical solutions, discussing their merits and drawbacks, and offers optimization strategies. Lastly, the paper presents a forward-looking perspective on potential research directions in this field from four angles.

show abstract