广西民族大学学报（自然科学版）2026，Vol.32Issue(1)：76-85,10.
基于三维高斯泼溅的文本指导三维目标检测分割方法与应用
Text-Guided 3D Object Detection and Segmentation Based on 3D Gaussian Splatting:Methods and Applications
摘要
Abstract
With advances in 3D reconstruction,semantic understanding of open-world scenes has gained growing attention.Text-guided 3D object detection and segmentation,recognized for their open-vocabulary generalization,are becoming crucial in human-computer interaction and scene interpretation.This paper reviews recent methods based on 3D Gaussian Splatting,categorizing them into direct supervision and cluster alignment according to how they constrain textual and geometric features.We compare their core ideas and implementations,summarize applications in autonomous driving,smart homes,AgriTech,and VR/AR,discuss challenges in cross-modal alignment and real-time interaction,and point to future research directions.关键词
三维场景表示/神经辐射场/三维高斯泼溅/开放词汇理解/多模态学习Key words
3D scene representation/Neural Radiance Fields/3D Gaussian Splatting/Open-vocabulary understanding/Multimodal learning分类
信息技术与安全科学引用本文复制引用
曾芊,蒋权,俞霆锋,李诚瑜..基于三维高斯泼溅的文本指导三维目标检测分割方法与应用[J].广西民族大学学报（自然科学版）,2026,32(1):76-85,10.基金项目
广西科技计划项目(桂科AD21220002). （桂科AD21220002）
