通过图引导的双层增强，提升3D场景分割的生成质量与模型性能。
Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation
- 用真实数据统计构建物体关系图，指导场景生成。
- 局部约束确保几何合理与语义一致，全局约束保持场景拓扑结构。
- 适用于需要高质量数据增强的3D分割任务，尤其适合室内室外场景。
3D点云分割旨在为场景中每个点分配语义标签，实现细粒度空间理解。现有方法通常采用数据增强缓解大规模标注负担，但多数策略仅关注局部变换或语义重组，缺乏对场景内全局结构依赖的考虑。为此，我们提出一种图引导的双层约束数据增强框架，用于生成更真实的3D场景。该方法从真实数据中学习物体关系统计，构建引导图以指导场景生成。局部约束确保物体间的几何合理性与语义一致性，全局约束则通过将生成布局与引导图对齐，维持场景的拓扑结构。在室内与室外数据集上的大量实验表明，该框架能生成多样且高质量的增强场景，显著提升多种分割模型的性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。