EUVIMEDEUVIMED entdecken
Crossref

ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments With Vision Foundation Models

Ying Zhang, Maoliang Yin, Wenfu Bi, Haibao Yan, Shaohan Bian, Cui-Hua Zhang, Changchun Hua

IEEE Transactions on Robotics · 2025 · 41 · 1568-1580

DOI: 10.1109/tro.2025.3539198 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2025. Verfasst von Ying Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hebei Province, Science Research Project of Hebei Education Department.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Service robots operating in unstructured environments must effectively recognize and segment unknown objects to enhance their functionality. Traditional supervised learning-based segmentation techniques require extensive annotated datasets, which are impractical for the diversity of objects encountered in real-world scenarios. Unseen object instance segmentation (UOIS) methods aim to address this by training models on synthetic data to generalize to novel objects, but they often suffer from the simulation-to-reality gap. This article proposes a novel approach (ZISVFM) for solving UOIS by leveraging the powerful zero-shot capability of the segment anything model (SAM) and explicit visual representations from a self-supervised vision transformer (ViT). The proposed framework operates in the following three stages: generating object-agnostic mask proposals from colorized depth images using SAM, refining these proposals using attention-based features from the self-supervised ViT to filter nonobject masks, and applying K-Medoids clustering to generate point prompts that guide SAM toward precise object segmentation. Experimental validation on two benchmark datasets and a self-collected dataset demonstrates the superior performance of ZISVFM in complex environments, including hierarchical settings such as cabinets, drawers, and handheld objects.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hebei Province
  • Science Research Project of Hebei Education Department
  • S&T Program of Hebei

Zitieren

APA

Zhang, Y., Yin, M., Bi, W., Yan, H., Bian, S., Zhang, C., & Hua, C. (2025). ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments With Vision Foundation Models. IEEE Transactions on Robotics, 41, 1568-1580. https://doi.org/10.1109/tro.2025.3539198

Vancouver

Zhang Y, Yin M, Bi W, Yan H, Bian S, Zhang C, et al. ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments With Vision Foundation Models. IEEE Transactions on Robotics. 2025;41:1568-1580. doi:10.1109/tro.2025.3539198

BibTeX
@article{Zhang2025,
  author = {Zhang, Ying and Yin, Maoliang and Bi, Wenfu and Yan, Haibao and Bian, Shaohan and Zhang, Cui-Hua and Hua, Changchun},
  title = {ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments With Vision Foundation Models},
  journal = {IEEE Transactions on Robotics},
  year = {2025},
  volume = {41},
  pages = {1568--1580},
  doi = {10.1109/tro.2025.3539198}
}
Kostenlos starten →