EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Framework for Interactive 3D Segmentation with Adaptive Masking and Fine-Grained Version Control

Tin Long Leung, Maral Bahari, Tun Jian Tan, Pin Siang Tan, Yu-Hsing Wang

ACM Transactions on Intelligent Systems and Technology · 28.02.2027 · 18 (1) · 1-35

DOI: 10.1145/3845998 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 29.10.2026. Verfasst von Tin Long Leung und 4 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: HKUST-Bright Dream Robotics Joint Research Institute, Hong Kong Research Grants Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fine-tuning remains an important step in adapting 3D foundation models to downstream applications, but it is laborious and time-consuming to annotate training datasets in 3D. Existing semi-automatic annotation methods for segmentation masks fail to generalize beyond RGB point cloud data and are difficult to control. While a number of 3D annotation interfaces provide undo/redo functionality to help correct mistakes, they lack a comprehensive data versioning strategy, limiting the potential for user analysis and quality control. To tackle these issues, we present DynamicSAM Annotator, an AI-assisted point segmentation framework with the following contributions: (1) a novel interactive 3D point cloud segmentation model that exclusively uses XYZ coordinates with an adaptive thresholding mechanism in segmentation masks; (2) a 3D annotation platform to enable efficient 3D point cloud annotation for semantic and instance segmentation tasks; and (3) a fine-grained version control system that efficiently persists each annotation operation to disk using Git-like operations. Rigorous evaluations across seven benchmark datasets demonstrate DynamicSAM’s effectiveness in both indoor and outdoor environments, achieving an average Intersection over Union (IoU) of 59.6% for a single click, highlighting the model’s outstanding generalization capabilities. Meanwhile, our simulated benchmark shows that our version control system maintains sub-second latency even with tens of thousands of snapshots stored. Our code is publicly available at: https://github.com/DESRLab/dynamic-sam .

Förderung

  • HKUST-Bright Dream Robotics Joint Research Institute
  • Hong Kong Research Grants Council

Zitieren

APA

Leung, T. L., Bahari, M., Tan, T. J., Tan, P. S., & Wang, Y. (2027). A Framework for Interactive 3D Segmentation with Adaptive Masking and Fine-Grained Version Control. ACM Transactions on Intelligent Systems and Technology, 18(1), 1-35. https://doi.org/10.1145/3845998

Vancouver

Leung TL, Bahari M, Tan TJ, Tan PS, Wang Y. A Framework for Interactive 3D Segmentation with Adaptive Masking and Fine-Grained Version Control. ACM Transactions on Intelligent Systems and Technology. 2027;18(1):1-35. doi:10.1145/3845998

BibTeX
@article{Leung2027,
  author = {Leung, Tin Long and Bahari, Maral and Tan, Tun Jian and Tan, Pin Siang and Wang, Yu-Hsing},
  title = {A Framework for Interactive 3D Segmentation with Adaptive Masking and Fine-Grained Version Control},
  journal = {ACM Transactions on Intelligent Systems and Technology},
  year = {2027},
  volume = {18},
  number = {1},
  pages = {1--35},
  doi = {10.1145/3845998}
}
Kostenlos starten →