EUVIMEDEUVIMED entdecken
Crossref

Diffusion-Based Contextual Reconstruction for Point Cloud Segmentation with Limited Annotations

Jiawei Lian, Zhengxue Wang, Wentao Qu, Haobo Jiang, Le Hui, Jian Yang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6780-6788

DOI: 10.1609/aaai.v40i8.37610 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jiawei Lian und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Point cloud semantic segmentation is fundamental to 3D scene understanding, but dense annotation requirements limit scalability. Although recent label propagation and contrastive learning methods enhance local consistency, the incomplete object coverage caused by sparse annotations hinders global context modeling, ultimately limiting overall performance. To this end, we propose a diffusion-based contextual reconstruction framework for point cloud semantic segmentation with limited annotations. At its core, our framework guides denoising with semantic predictions, using better context reconstruction to enhance the conditional model for better segmentation. Specifically, our contributions include: (1) Diffusion-based segmentation framework: reconstructs contextual semantics from noise under conditional guidance, sharing the decoder with the segmentation module for robust contextual semantic learning. (2) Dynamically aggregates local context from segmentation features and guides denoising with global spatial structure, significantly enhancing denoising quality and contextual awareness. Notably, we pioneer diffusion models for 3D semantic segmentation with limited annotations, enabling efficient single-step inference. Experiments show robustness across varying annotation ratios and state-of-the-art performance on benchmarks.

Zitieren

APA

Lian, J., Wang, Z., Qu, W., Jiang, H., Hui, L., & Yang, J. (2026). Diffusion-Based Contextual Reconstruction for Point Cloud Segmentation with Limited Annotations. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6780-6788. https://doi.org/10.1609/aaai.v40i8.37610

Vancouver

Lian J, Wang Z, Qu W, Jiang H, Hui L, Yang J. Diffusion-Based Contextual Reconstruction for Point Cloud Segmentation with Limited Annotations. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6780-6788. doi:10.1609/aaai.v40i8.37610

BibTeX
@article{Lian2026,
  author = {Lian, Jiawei and Wang, Zhengxue and Qu, Wentao and Jiang, Haobo and Hui, Le and Yang, Jian},
  title = {Diffusion-Based Contextual Reconstruction for Point Cloud Segmentation with Limited Annotations},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {8},
  pages = {6780--6788},
  doi = {10.1609/aaai.v40i8.37610}
}
Kostenlos starten →