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

TL;DR

This paper introduces a graph-guided data augmentation framework for 3D scene segmentation that models global and local scene structures to improve the realism and diversity of augmented data, enhancing segmentation accuracy.

Contribution

It proposes a dual-level augmentation method using guiding graphs to incorporate global scene structure and local geometric and semantic constraints, which was lacking in prior augmentation strategies.

Findings

Improves segmentation accuracy across multiple datasets.

Generates diverse and realistic augmented scenes.

Enhances model robustness with structured augmentation.

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.