%0 Journal Article
%T 卫星可见光多视角影像的表面重构综述<br>A Review of Research on 3D Reconstruction from Satellite Visible Light Imagery
%A 邓毅
%A 解文彬
%J Computer Science and Application
%P 54-63
%@ 2161-881X
%D 2025
%I Hans Publishing
%R 10.12677/csa.2025.153057
%X 在卫星多视角影像三维重构领域的关键技术领域中&#65292;主流的方法主要为基于立体匹配的点云生成与表面重构方法&#65292;包括三角化方法、模板先验、建模先验及深度学习等方法。而对于新兴的重构技术神经辐射场&#65292;特别探讨了其原理与工作流程&#65292;及其在稀疏视角和复杂光照条件下的优势与研究进展。最后&#65292;文章总结了未来的发展趋势&#65292;并提出了未来的研究方向&#65292;涵盖了3DGS大规模场景重建技术、语义感知辅助建模等方面。<br>This paper reviews key technologies in satellite image 3D reconstruction, focusing on stereo matching-based point cloud generation, triangulation, modeling priors, and deep learning methods. It discusses the principles and advantages of Neural Radiance Fields (NeRF) in sparse views and complex lighting. The role of geometric information extraction in surface reconstruction and the current research status of traditional and deep learning methods are also highlighted. Future research directions include 3DGS for large-scale scene reconstruction and so on.
%K 卫星光学影像&#65292
%K 立体匹配&#65292
%K 表面重构&#65292
%K 神经辐射场<br>Satellite Visible Light Imagery
%K Stereo Matching
%K Surface Reconstruction
%K Neural Radiance Fields
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=109123