EUVIMEDEUVIMED entdecken
Crossref

Dynamic 3D Point Cloud Sequences as 2D Videos

Yiming Zeng, Junhui Hou, Qijian Zhang, Siyu Ren, Wenping Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 9371-9386

DOI: 10.1109/tpami.2024.3421359 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Yiming Zeng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 82 Literaturangaben. Gefördert von: Hong Kong Research Grants Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both spatial and temporal domains poses significant challenges to effective and efficient processing. Existing deep point cloud sequence modeling approaches imitate the mature 2D video learning mechanisms by developing complex spatio-temporal point neighbor grouping and feature aggregation schemes, often resulting in methods lacking effectiveness, efficiency, and expressive power. In this paper, we propose a novel generic representation called Structured Point Cloud Videos (SPCVs). Intuitively, by leveraging the fact that 3D geometric shapes are essentially 2D manifolds, SPCV re-organizes a point cloud sequence as a 2D video with spatial smoothness and temporal consistency, where the pixel values correspond to the 3D coordinates of points. The structured nature of our SPCV representation allows for the seamless adaptation of well-established 2D image/video techniques, enabling efficient and effective processing and analysis of 3D point cloud sequences. To achieve such re-organization, we design a self-supervised learning pipeline that is geometrically regularized and driven by self-reconstructive and deformation field learning objectives. Additionally, we construct SPCV-based frameworks for both low-level and high-level 3D point cloud sequence processing and analysis tasks, including action recognition, temporal interpolation, and compression. Extensive experiments demonstrate the versatility and superiority of the proposed SPCV, which has the potential to offer new possibilities for deep learning on unstructured 3D point cloud sequences.

Förderung

  • Hong Kong Research Grants Council

Zitieren

APA

Zeng, Y., Hou, J., Zhang, Q., Ren, S., & Wang, W. (2024). Dynamic 3D Point Cloud Sequences as 2D Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9371-9386. https://doi.org/10.1109/tpami.2024.3421359

Vancouver

Zeng Y, Hou J, Zhang Q, Ren S, Wang W. Dynamic 3D Point Cloud Sequences as 2D Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):9371-9386. doi:10.1109/tpami.2024.3421359

BibTeX
@article{Zeng2024,
  author = {Zeng, Yiming and Hou, Junhui and Zhang, Qijian and Ren, Siyu and Wang, Wenping},
  title = {Dynamic 3D Point Cloud Sequences as 2D Videos},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {9371--9386},
  doi = {10.1109/tpami.2024.3421359}
}
Kostenlos starten →