EUVIMEDEUVIMED entdecken
Crossref

Towards Efficient and Effective Interactive 3D Segmentation

Wei Cong, Yang Cong, Jiahua Dong, Gan Sun

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3425-3433

DOI: 10.1609/aaai.v40i5.37339 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Wei Cong und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interactive 3D segmentation embodies an advanced human-in-the-loop paradigm, where a model iteratively refines the segmentation of interested objects within a 3D point cloud through user feedback. Existing methods have achieved notable advancements at the expense of substantial resource consumption. To address this challenge, we introduce E2I3D, an efficient and effective model for interactive 3D segmentation. Specifically, we propose a two-stage efficiency-to-effectiveness framework to decouple efficiency and effectiveness, avoiding the high training cost of joint optimization. For efficiency in the first stage, we present heterogeneous pruning, which reliably compresses the model by ranking and pruning the constructed heterogeneous groups separately based on gradient compensation. For effectiveness in the second stage, we design hierarchical click-aware attention that integrates geometric details from high-resolution features with global context from low-resolution features to enhance click-guided interaction. Extensive experiments across public datasets demonstrate that E2I3D exceeds state-of-the-art methods in both efficiency and effectiveness. For instance, on the KITTI-360 dataset, E2I3D boosts the IoU for interactive single-object segmentation from 44.4% to 49.0% with 5 user clicks, while simultaneously reducing parameters from 39.3M to 5.7M.

Zitieren

APA

Cong, W., Cong, Y., Dong, J., & Sun, G. (2026). Towards Efficient and Effective Interactive 3D Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3425-3433. https://doi.org/10.1609/aaai.v40i5.37339

Vancouver

Cong W, Cong Y, Dong J, Sun G. Towards Efficient and Effective Interactive 3D Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3425-3433. doi:10.1609/aaai.v40i5.37339

BibTeX
@article{Cong2026,
  author = {Cong, Wei and Cong, Yang and Dong, Jiahua and Sun, Gan},
  title = {Towards Efficient and Effective Interactive 3D Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {3425--3433},
  doi = {10.1609/aaai.v40i5.37339}
}
Kostenlos starten →