Few-Shot Remote Sensing Novel View Synthesis with Geometry Constraint NeRF  

作　　者：Jiaming Kang Keyan Chen Zhengxia Zou Zhenwei Shi 

机构地区：[1]Image Processing Center,School of Astronautics Beihang University,Beijing 100191,P.R.China [2]Department of Guidance,Navigation and Control School of Astronautics,Beihang University Beijing 100191,P.R.China

出　　处：《Guidance, Navigation and Control》2024年第3期70-91,共22页制导、导航与控制(英文)

基　　金：supported by the National Natural Science Foundation of China under Grants 62125102;the Beijing Natural Science Foundation under Grant JL23005;the Fundamental Research Funds for the Central Universities

摘　　要：Novel View Synthesis(NVS) is an important task for 3D interpretation in remote sensing scenes, which also benefits vicinagearth security by enhancing situational awareness capabilities. Recently, NVS methods based on Neural Radiance Fields(Ne RFs) have attracted increasing attention for self-supervised training and highly photo-realistic synthesis results.However, it is still challenging to synthesize novel view images in remote sensing scenes, given the complexity of land covers and the sparsity of input multi-view images. In this paper, we propose a novel NVS method named FRe SNe RF, which combines Image-Based Rendering(IBR) and Ne RF to achieve high-quality results in remote sensing scenes with sparse input. We effectively solve the degradation problem by adopting the sampling space annealing method.Additionally, we introduce depth smoothness based on the segmentation mask to constrain the scene geometry. Experiments on multiple scenes show the superiority of our proposed FRe SNe RF over other methods.

关 键 词：Vicinagearth security remote sensing novel view synthesis image-based rendering neural radiance field 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置] TP18[自动化与计算机技术—控制科学与工程]