西华大学学报（自然科学版）2025，Vol.44Issue(6)：70-81,12.DOI:10.12198/j.issn.1673-159X.5394
基于边界预测辅助的稀疏深度图像修复
Sparse Depth Image Completion Based on Boundary Prediction Assistance
周恒 1李滔 2孙明明 2武丹丹 2周明会2
作者信息
- 1. 西华大学电气与电子信息学院,四川 成都 610039||四川工业科技学院,四川 德阳 618500
- 2. 西华大学电气与电子信息学院,四川 成都 610039
- 折叠
摘要
Abstract
Depth images completion aims to recover dense depth images from sparse depth images.However,the depth images restored by many current depth completion algorithms often suffer from prob-lems such as missing detail structures,depth discontinuities and blurred boundaries.To address these prob-lems,this paper proposes a sparse depth completion method based on boundary prediction assistance,in which depth image completion is the main task and boundary prediction is the auxiliary task.A cross-guid-ance module is proposed to realize information interaction between the main task and the auxiliary task and provide effective boundary constraint for the main completion task.Moreover,an intermediate feature ex-traction module is used to extract multiple perceptual field features for scene context learning.In this paper,a series of experiments were conducted on the indoor dataset NYUv2 and the outdoor dataset KITTI,the experimental results prove the effectiveness of the proposed algorithms and modules,and it is superior to some mainstream depth completion methods in qualitative and quantitative comparison.关键词
深度修复/多任务学习/图像处理/深度图像/图像识别Key words
depth completion/multi-task learning/image processing/depth image/image recognition分类
信息技术与安全科学引用本文复制引用
周恒,李滔,孙明明,武丹丹,周明会..基于边界预测辅助的稀疏深度图像修复[J].西华大学学报（自然科学版）,2025,44(6):70-81,12.
