LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learning

TL;DR

This paper introduces a novel active learning framework for 3D point cloud segmentation that uses large language models to create hierarchical label structures and guide sample selection, significantly improving annotation efficiency.

Contribution

It is the first to integrate LLMs for hierarchical taxonomy construction and uncertainty propagation in 3D point cloud active learning, enhancing label-aware sampling.

Findings

Up to 4% mIoU improvement with minimal annotation (0.02%)

Outperforms existing methods on S3DIS and ScanNet v2 datasets

Demonstrates the effectiveness of hierarchical uncertainty modeling

Abstract

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.