English

Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation

Computer Vision and Pattern Recognition 2025-07-31 v1

Abstract

3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation. However, most augmentation strategies only focus on local transformations or semantic recomposition, lacking the consideration of global structural dependencies within scenes. To address this limitation, we propose a graph-guided data augmentation framework with dual-level constraints for realistic 3D scene synthesis. Our method learns object relationship statistics from real-world data to construct guiding graphs for scene generation. Local-level constraints enforce geometric plausibility and semantic consistency between objects, while global-level constraints maintain the topological structure of the scene by aligning the generated layout with the guiding graph. Extensive experiments on indoor and outdoor datasets demonstrate that our framework generates diverse and high-quality augmented scenes, leading to consistent improvements in point cloud segmentation performance across various models.

Keywords

Cite

@article{arxiv.2507.22668,
  title  = {Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation},
  author = {Hongbin Lin and Yifan Jiang and Juangui Xu and Jesse Jiaxi Xu and Yi Lu and Zhengyu Hu and Ying-Cong Chen and Hao Wang},
  journal= {arXiv preprint arXiv:2507.22668},
  year   = {2025}
}

Comments

15 pages, 11 figures, to be published in ACMMM 2025 Conference

R2 v1 2026-07-01T04:26:02.463Z