EUVIMEDEUVIMED entdecken
Crossref

Topology-Aware Keypoint Detection via Skeleton-Based Shape Matching

Yushi Li, Pengfei Li, Meng Xu, Yunzhe Wang, Chengtao Ji, Yu Han, Rong Chen

IEEE Transactions on Consumer Electronics · 2025-02 · 71 (1) · 367-378

DOI: 10.1109/tce.2024.3518458 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-02. Verfasst von Yushi Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: Industry collaboration funding, Basic and Applied Basic Research Foundation of Guangdong Province, Xi'an Jiaotong-Liverpool University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

3D keypoint detection endeavors to identify well-aligned and semantically consistent elements that reflect object shapes within point clouds, which plays a significant role in wide-ranging applications such as navigation and object tracking based on mobile devices. While existing approaches prioritize either salient features or statistic distributions for alignment, they overlook the underlying spatial topology of shapes. Although some recent methods take potential skeletons into account, they fail to associate this representation with local and global topology, thus reconciling comprehensive coverage and semantic awareness. To address this, we reckon keypoint detection as the skeleton-based shape matching and propose a two-branch framework that explicitly localizes the keypoints with broad coverage and semantic coherence in an unsupervised manner. Specifically, one branch incorporates the keypoint detector with a skeleton generator to infer the coarse skeletons that represent the global topology. Meanwhile, another branch leverages skeletal sphere estimation to generate the skeletal point set that sustains the local structures, serving as the foundation for optimizing the skeletons formed by keypoints. Since these skeletal representations capture both the structural essence and semantic attributes of a shape, our model is capable of extracting semantically rich keypoints with good alignment. We extensively evaluate our method on different datasets to demonstrate its effectiveness and competitiveness in 3D keypoint detection.

Förderung

  • Industry collaboration funding
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Xi'an Jiaotong-Liverpool University

Zitieren

APA

Li, Y., Li, P., Xu, M., Wang, Y., Ji, C., Han, Y., & Chen, R. (2025). Topology-Aware Keypoint Detection via Skeleton-Based Shape Matching. IEEE Transactions on Consumer Electronics, 71(1), 367-378. https://doi.org/10.1109/tce.2024.3518458

Vancouver

Li Y, Li P, Xu M, Wang Y, Ji C, Han Y, et al. Topology-Aware Keypoint Detection via Skeleton-Based Shape Matching. IEEE Transactions on Consumer Electronics. 2025;71(1):367-378. doi:10.1109/tce.2024.3518458

BibTeX
@article{Li2025,
  author = {Li, Yushi and Li, Pengfei and Xu, Meng and Wang, Yunzhe and Ji, Chengtao and Han, Yu and Chen, Rong},
  title = {Topology-Aware Keypoint Detection via Skeleton-Based Shape Matching},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2025},
  volume = {71},
  number = {1},
  pages = {367--378},
  doi = {10.1109/tce.2024.3518458}
}
Kostenlos starten →