EUVIMEDEUVIMED entdecken
Crossref

Zero-Shot Single-View Point Cloud Reconstruction via Cross-Category Knowledge Transferring

Lvlong Lai, Jian Chen, Qingyao Wu

IEEE Transactions on Multimedia · 2024 · 26 · 1448-1459

DOI: 10.1109/tmm.2023.3282467 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Multimedia, 2024. Verfasst von Lvlong Lai und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Tip-top Scientific and Technical Innovative Youth Talents of Guangdong Special Support Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single-view point cloud reconstruction aims to generate a 3D point cloud of an object given one 2D image taken from an arbitrary viewpoint. Most previous works assume that all the test categories have been present to the model during training. However, it is impossible to know all the test categories that the model will meet in advance. And we discover these methods can not deal with novel categories well. Therefore, in this article, we investigate a more realistic and challenging setting of single-view point cloud reconstruction, zero-shot, where the model's performance on novel categories is pursued. Towards this task, we propose the Cross-Category Knowledge Transferring Network (CCKTN), which maintains a knowledge bank to mine transferable knowledge from known categories to help reconstruct novel categories. Additionally, we conduct auxiliary learning for the point cloud reconstruction model with the point cloud autoencoder via sharing the same knowledge bank. This design enables the knowledge bank to collect more fruitful 3D knowledge of point clouds. Moreover, we devise a diversity loss regularization for the knowledge vectors to guarantee their diversities, further enhancing CCKTN's performance. Comprehensive experiments conducted on ShapeNet and ModelNet datasets show CCKTN's superiority towards existing methods and demonstrate CCKTN's effectiveness for reconstructing novel category objects.

Förderung

  • National Natural Science Foundation of China
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Tip-top Scientific and Technical Innovative Youth Talents of Guangdong Special Support Program
  • 2022 Tencent Wechat Rhino-Bird Focused Research Program
  • Tencent WeChat
  • Major Key Project of PCL

Zitieren

APA

Lai, L., Chen, J., & Wu, Q. (2024). Zero-Shot Single-View Point Cloud Reconstruction via Cross-Category Knowledge Transferring. IEEE Transactions on Multimedia, 26, 1448-1459. https://doi.org/10.1109/tmm.2023.3282467

Vancouver

Lai L, Chen J, Wu Q. Zero-Shot Single-View Point Cloud Reconstruction via Cross-Category Knowledge Transferring. IEEE Transactions on Multimedia. 2024;26:1448-1459. doi:10.1109/tmm.2023.3282467

BibTeX
@article{Lai2024,
  author = {Lai, Lvlong and Chen, Jian and Wu, Qingyao},
  title = {Zero-Shot Single-View Point Cloud Reconstruction via Cross-Category Knowledge Transferring},
  journal = {IEEE Transactions on Multimedia},
  year = {2024},
  volume = {26},
  pages = {1448--1459},
  doi = {10.1109/tmm.2023.3282467}
}
Kostenlos starten →