面向卫星遥感图像场景重建的神经辐射场方法综述

A Review of Neural Radiance Field Approaches for Scene Reconstruction of Satellite Remote Sensing Imagery

随着高分辨率卫星遥感图像成为认知地理空间不可或缺的重要手段,卫星遥感图像在城市建图、生态监测和导航等领域发挥着日益重要的作用,利用卫星遥感图像进行地球表面大规模3维重建成为了计算机视觉和摄影测量领域的研究热点。神经辐射场(NeRF)利用可微渲染学习场景的隐式表示,在复杂场景新视图合成任务中实现了逼真的视觉效果,并在3维场景重建和渲染领域获得了极大的关注。近期的研究主要集中在利用神经辐射场技术,从卫星遥感图像中提取场景表示及其重建。面向卫星遥感图像的神经辐射场方法主要集中在光线空间优化、场景表示优化以及模型高效训练3方面。该文全面归纳了神经辐射场技术在卫星遥感应用中的最新进展。首先介绍神经辐射场技术的基本概念及相关数据集。然后提出一个面向卫星遥感图像的神经辐射场方法分类框架,用于系统性地回顾和整理该技术在卫星遥感领域的研究进展。接着详述了神经辐射场技术在实际卫星遥感场景应用中的相关成果。最后,基于当前研究所面临的问题和挑战进行分析和讨论,同时对未来的发展趋势和研究方向进行了展望。

High-resolution satellite remote sensing images have been recognized as an indispensable means for understanding geographical spaces,and their role in areas such as urban mapping,ecological monitoring,and navigation,has become increasingly important.The use of satellite remote sensing images for large-scale 3D reconstruction of the Earth’s surface is currently a subject of active research in the fields of computer vision and photogrammetry.Neural Radiance Fields(NeRF),which utilizes differentiable rendering to learn implicit representations of scenes,has achieved the most realistic visual effects in novel view synthesis tasks of complex scenes and has attracted significant attention in the field of 3D scene reconstruction and rendering.Recent research has been primarily focused on using neural radiance field technology to extract scene representation and reconstruction from satellite remote sensing images.Ray space optimization,scene representation optimization,and efficient model training are mainly focused on by the neural radiance field methods for satellite remote sensing images.The latest progress in the application of neural radiance field technology in satellite remote sensing is comprehensively summarized in this paper.First,the basic concepts of neural radiance field technology and related datasets are introduced.Then a classification framework of neural radiance field methods for satellite remote sensing images is proposed to systematically review and organize the research progress of this technology in the field of satellite remote sensing.The relevant results of the application of neural radiance field technology in actual satellite remote sensing scenarios are detailed.Finally,analysis and discussion are conducted based on the problems and challenges faced by current research,and future development trends and research directions are prospected.