用大模型构建分层标签结构，提升3D点云标注效率
LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learning
- 用大模型自动生成多层级语义分类体系
- 递归传播不确定性，实现有语义的点云选样
- 低预算下性能提升4%，适合高效点云标注
我们提出一种新型主动学习框架，用于3D点云语义分割。首次将大语言模型（LLM）引入，用于构建分层标签结构并指导基于不确定性的样本选择。与以往将标签视为扁平独立的方法不同，本方法通过LLM提示自动生成多层次语义分类体系，并引入递归不确定性投影机制，实现跨层级的不确定性传播。该机制使采样兼具空间多样性与标签感知性，符合3D场景的内在语义结构。在S3DIS和ScanNet v2上的实验表明，在极低标注预算（如0.02%）下，本方法可实现高达4%的mIoU提升，显著优于现有基线。结果凸显了大模型作为3D视觉知识先验的巨大潜力，并确立了层次化不确定性建模作为高效点云标注的强大范式。
原文摘要 · Abstract (English)
We present a novel active learning framework for 3D point cloud semantic segmentation that, for the first time, integrates large language models (LLMs) to construct hierarchical label structures and guide uncertainty-based sample selection. Unlike prior methods that treat labels as flat and independent, our approach leverages LLM prompting to automatically generate multi-level semantic taxonomies and introduces a recursive uncertainty projection mechanism that propagates uncertainty across hierarchy levels. This enables spatially diverse, label-aware point selection that respects the inherent semantic structure of 3D scenes. Experiments on S3DIS and ScanNet v2 show that our method achieves up to 4% mIoU improvement under extremely low annotation budgets (e.g., 0.02%), substantially outperforming existing baselines. Our results highlight the untapped potential of LLMs as knowledge priors in 3D vision and establish hierarchical uncertainty modeling as a powerful paradigm for efficient point cloud annotation.
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。