EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Self-Supervised Text-Driven Point Cloud Upsampling via Semantic Text Guidance

Zhiyong Zhang iD, Meiling Qiu, Shuo Chen, Ruyu Liu iD, Jianhua Zhang iD, Shengyong Chen

Journal of Imaging · 11.05.2026 · 12 (5) · 204

DOI: 10.3390/jimaging12050204 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 11.05.2026. Verfasst von Zhiyong Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300000, China. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Point cloud upsampling is a fundamental task in 3D vision, yet most existing methods adopt a global and uniform strategy, which is computationally inefficient and fails to address the need for region-specific refinement. To address this challenge, we propose PartSPUNet, a novel self-supervised, text-driven point cloud upsampling framework designed to enhance robotic perception through task-oriented local refinement. Inspired by the human cognitive process where high-level language instructions guide visual attention to specific regions of interest, our method allows an operator to use intuitive natural language prompts to direct the upsampling process. Specifically, PartSPUNet leverages a pretrained vision–language model to zero-shot localize the user-specified semantic part within a sparse point cloud. It then performs geometry-aware densification exclusively on this target region, recovering rich geometric details while preserving the global structure. Experimental results demonstrate that our approach significantly outperforms existing methods in reconstructing specified areas, offering a powerful and intuitive tool for enhancing the 3D perception pipeline in intelligent robotic systems.

Schlagwörter

Stichwörter der Autor:innen

biomimetic perceptionlanguage-guidedpoint cloud upsamplingvision–language model

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300000, China.
  • School of Information Science and Technology, Hangzhou Normal University, Hangzhou 310000, China.
  • Department of Technology, Management and Economics, Technical University of Denmark, 2800 Lyngby, Denmark.

ORCID-Profile: Zhiyong Zhang, Ruyu Liu, Jianhua Zhang

Zitieren

APA

Zhang, Z., Qiu, M., Chen, S., Liu, R., Zhang, J., & Chen, S. (2026). Self-Supervised Text-Driven Point Cloud Upsampling via Semantic Text Guidance. Journal of Imaging, 12(5), 204. https://doi.org/10.3390/jimaging12050204

Vancouver

Zhang Z, Qiu M, Chen S, Liu R, Zhang J, Chen S. Self-Supervised Text-Driven Point Cloud Upsampling via Semantic Text Guidance. Journal of Imaging. 2026;12(5):204. doi:10.3390/jimaging12050204

BibTeX
@article{Zhang2026,
  author = {Zhang, Zhiyong and Qiu, Meiling and Chen, Shuo and Liu, Ruyu and Zhang, Jianhua and Chen, Shengyong},
  title = {Self-Supervised Text-Driven Point Cloud Upsampling via Semantic Text Guidance},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {5},
  pages = {204},
  doi = {10.3390/jimaging12050204}
}
Kostenlos starten →