西华大学学报（自然科学版）2026，Vol.45Issue(4)：48-59,97,13.DOI:10.12198/j.issn.1673-159X.5815
基于语义边缘引导的无监督深度图像修复
Unsupervised Depth Completion Guided by Semantic Edges
摘要
Abstract
Currently,unsupervised depth completion techniques often encounter challenges in terms of restoration accuracy and detail preservation when dealing with images containing complex structures and fine textures.To this end,an unsupervised depth completion model guided by semantic segmentation edges was proposed in this paper.By introducing a semantic edge branch,the edge information of semantic seg-mentation features was utilized to precisely delineate object contours,guiding the network to generate more natural and coherent restoration results.Through a dual-attention feature fusion module,depth features and RGB image features were effectively combined,significantly enhancing the model's capability to extract and learn structural features.On the KITTI dataset,the RMSE index decreases by approximately 2.00%compared with other models,and on the VOID dataset,the RMSE index decreases by approximately 9.18%compared with other models,indicating that the model is effective.关键词
无监督深度图像修复/语义边缘分支/双注意力特征融合/图像处理/深度图像Key words
unsupervised depth completion/semantic edge branch/dual-attention feature fusion/image processing/depth image分类
信息技术与安全科学引用本文复制引用
武丹丹,李滔,李胜科..基于语义边缘引导的无监督深度图像修复[J].西华大学学报（自然科学版）,2026,45(4):48-59,97,13.基金项目
四川省科技厅项目(2021YJ0109). （2021YJ0109）
