Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation
This addresses the annotation bottleneck for 3D scene understanding, though it appears incremental as it builds on existing augmentation approaches.
The paper tackles the problem of limited annotated data for 3D point cloud segmentation by proposing a graph-guided data augmentation framework that generates realistic scenes using dual-level constraints, resulting in consistent improvements in segmentation performance across various models on indoor and outdoor datasets.
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.