青岛大学学报（自然科学版）2026，Vol.39Issue(2)：40-47,8.DOI:10.3969/j.issn.1006-1037.2026.02.06
基于细粒度文本特征融合的跨模态单目深度估计模型
Cross-modal Monocular Depth Estimation Model Based on Fine-grained Textual Feature Fusion
摘要
Abstract
In the field of monocular depth estimation for complex scenes,a key problem is the occurrence of depth discontinuities and blurred edges caused by irregular objects such as people or animals.To address this issue,a model named Multiple Fine-Grained Textual Features Fusion for Monocular Depth Estimation(MFGT-Depth)was designed.The Gaussian Mixture Model(GMM)was used to probabilistically model latent semantic hier-archy and complex relationships among descriptions.For efficient cross-modal alignment,the cross-modal module then adaptively fused the text features and the image features ex-tracted by the image encoder.Experiments show that MFGT-Depth achieves significant improvements in major metrics on training datasets,reducing RMSE by 4.8%on the KITTI dataset,and exhibits strong generalization with significantly improved accuracy and robustness for depth estimation in scenes with irregular objects relative to Depth Any-thing V2.关键词
单目深度估计/文本特征融合/高斯混合模型/细粒度/跨模态/深度学习/计算机视觉Key words
monocular depth estimation/textual feature fusion/Gaussian Mixture Model/fine-grained/cross-modal/deep learning/computer vision分类
信息技术与安全科学引用本文复制引用
谭莉,王文龙,周萌萌,刘小娇,杨杰..基于细粒度文本特征融合的跨模态单目深度估计模型[J].青岛大学学报（自然科学版）,2026,39(2):40-47,8.基金项目
山东省自然科学基金(批准号:ZR2021MF025)资助. （批准号:ZR2021MF025）
