EUVIMEDEUVIMED entdecken
Crossref

PU-GSM: A Latent Geometry-Guided Self-Similarity Model for Point Cloud Upsampling

Hao Liu, Hui Yuan, Raouf Hamzaoui, Weiqing Yan

IEEE Transactions on Circuits and Systems for Video Technology · 2025-11 · 35 (11) · 11514-11526

DOI: 10.1109/tcsvt.2025.3612698 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-11. Verfasst von Hao Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, High-End Foreign Experts Recruitment Plan of Chinese Ministry of Human Resources and Social Security, Taishan Scholar Project of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing point cloud upsampling methods typically treat upsampling as a local interpolation problem, neglecting the importance of global correlations within point sets, which can limit their performance. To address this limitation, we exploit the inherent self-similarity of point clouds from a global perspective and propose PU-GSM, a latent geometry-guided self-similarity model for upsampling. We first generate a lower-resolution sparse sub-point cloud (SPC) by downsampling the input point cloud (IPC). Then, we introduce a latent geometry-guided self-similarity model (LGSM) that learns a point distribution on the underlying surface of SPC by exploiting the inherent self-similarity of IPC. Next, we reuse the LGSM for the remaining points (i.e., the points left after removing SPC from IPC). Afterward, we introduce a gradient-aware dual domain refiner to generate and calibrate the upsampled point cloud from the learned point distribution. Finally, we propose an inference-free latent vector matching approach to regularize the upsampled point cloud by enhancing the feature similarity between the upsampled point cloud and the ground truth in latent space. Extensive experiments show that PU-GSM achieves better upsampling results compared to state-of-the-art methods. Our code will be available at: https://github.com/liuhaoyun/PU-GSM

Förderung

  • National Natural Science Foundation of China
  • High-End Foreign Experts Recruitment Plan of Chinese Ministry of Human Resources and Social Security
  • Taishan Scholar Project of Shandong Province
  • Natural Science Foundation of Shandong Province
  • Shandong Provincial College Youth Innovation Team Project

Zitieren

APA

Liu, H., Yuan, H., Hamzaoui, R., & Yan, W. (2025). PU-GSM: A Latent Geometry-Guided Self-Similarity Model for Point Cloud Upsampling. IEEE Transactions on Circuits and Systems for Video Technology, 35(11), 11514-11526. https://doi.org/10.1109/tcsvt.2025.3612698

Vancouver

Liu H, Yuan H, Hamzaoui R, Yan W. PU-GSM: A Latent Geometry-Guided Self-Similarity Model for Point Cloud Upsampling. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(11):11514-11526. doi:10.1109/tcsvt.2025.3612698

BibTeX
@article{Liu2025,
  author = {Liu, Hao and Yuan, Hui and Hamzaoui, Raouf and Yan, Weiqing},
  title = {PU-GSM: A Latent Geometry-Guided Self-Similarity Model for Point Cloud Upsampling},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2025},
  volume = {35},
  number = {11},
  pages = {11514--11526},
  doi = {10.1109/tcsvt.2025.3612698}
}
Kostenlos starten →