LLM-Enhanced Semantic Segmentation of Large-Scale Urban LiDAR Point Clouds via Contextual Prompting
A contextual cue framework of "LiDAR semantics-large language model-retrieval-enhanced generation" is proposed, providing a new technical path for high-precision, fine-grained semantic segmentation of urban LiDAR point clouds and also offers a theoretical reference for promoting the in-depth application of large language models in 3D spatial intelligence.