计算机工程与应用2025，Vol.61Issue(6)：22-35,14.DOI:10.3778/j.issn.1002-8331.2405-0328
深度学习的多视角三维重建技术综述
Overview of Multi-View 3D Reconstruction Techniques in Deep Learning
摘要
Abstract
In order to solve the problems that classic multi-view 3D reconstruction methods are difficult to reconstruct complex objects and have poor reconstruction results,and to extend to high resolution,deep learning methods are intro-duced to reconstruct 3D models with higher accuracy.Thus multi-view 3D reconstruction algorithm using deep learning methods are systematically summarized,analyzed and compared,and the multi-view 3D reconstruction algorithms in recent years are classified and sorted out according to explicit geometry and implicit geometry representations.Neural implicit 3D reconstruction algorithms that combines implicit functions and volume rendering are mainly introduced,which currently have a high accuracy in reconstruction results,and the quantitative and qualitative analyses are conducted on some of these algorithms.In addition,commonly used datasets and evaluation indicators are listed,and the future research trends and development directions are discussed.关键词
深度学习/三维重建/神经隐式表示/体渲染Key words
deep learning/3D reconstruction/implicit neural representation/volume rendering分类
计算机与自动化引用本文复制引用
王文举,唐邦,顾泽骅,王森..深度学习的多视角三维重建技术综述[J].计算机工程与应用,2025,61(6):22-35,14.基金项目
上海市自然科学基金面上项目(Z-2019-309-007). （Z-2019-309-007）
