EUVIMEDEUVIMED entdecken
Crossref

Text‐Inspired Feature Refinement for Few‐Shot 3D Point Cloud Semantic Segmentation

Zihan Tang, Yong Zhao, Fan Zhong

Computer Graphics Forum · 13.11.2026

DOI: 10.1111/cgf.70635 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 13.11.2026. Verfasst von Zihan Tang und 2 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, State Key Laboratory of Computer Aided Design and Computer Graphics.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few‐shot 3D point cloud semantic segmentation aims to segment novel categories in 3D scenes with scarce labeled support samples. Recent studies have predominantly followed the prototype‐based paradigm, focusing mainly on prototype enhancement. However, they typically neglect the significance of feature representation, which is pivotal to segmentation accuracy. In this work, we propose a framework to explicitly refine 3D features by exploiting geometric dependencies and leveraging semantic knowledge from text. Specifically, we first introduce a Channel‐Aware Feature Purification (CAFP) module, which mines latent global intra‐channel correlations to purify 3D features for stronger discriminability. Secondly, we propose a Text‐Anchored Modality Adaptation (TAMA) module to enhance inter‐class separability and intra‐class compactness of 3D features while alleviating the support‐query gap under textual guidance. Within this module, class‐specific text embeddings serve as semantic anchors to drive the adaptive alignment of features. Moreover, we design a Text‐Geometry (TG) loss to further transfer inter‐class semantic relationships from text to 3D geometry, facilitating more precise separations between foreground and background points. Extensive experiments demonstrate the superiority of our method, outperforming state‐of‐the‐art approaches by margins of 5.69% and 9.66% in mIoU on S3DIS and ScanNet, respectively. Our code is available at: https://github.com/TZH716/TIFR .

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province
  • State Key Laboratory of Computer Aided Design and Computer Graphics

Zitieren

APA

Tang, Z., Zhao, Y., & Zhong, F. (2026). Text‐Inspired Feature Refinement for Few‐Shot 3D Point Cloud Semantic Segmentation. Computer Graphics Forum. https://doi.org/10.1111/cgf.70635

Vancouver

Tang Z, Zhao Y, Zhong F. Text‐Inspired Feature Refinement for Few‐Shot 3D Point Cloud Semantic Segmentation. Computer Graphics Forum. 2026. doi:10.1111/cgf.70635

BibTeX
@article{Tang2026,
  author = {Tang, Zihan and Zhao, Yong and Zhong, Fan},
  title = {Text‐Inspired Feature Refinement for Few‐Shot 3D Point Cloud Semantic Segmentation},
  journal = {Computer Graphics Forum},
  year = {2026},
  doi = {10.1111/cgf.70635}
}
Kostenlos starten →