Photogrammetry for Unconstrained Optical Satellite Imagery With Combined Neural Radiance Fields

被引：3

作者：

Li, Xiaohe ^{[1
]}

Fan, Zide ^{[1
]}

Liu, Xiaoxuan ^{[1
]}

Zhang, Yidan ^{[1
]}

Ge, Yunping ^{[1
]}

Wen, Lijie ^{[2
]}

机构：

[1] Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100045, Peoples R China

[2] Tsinghua Univ, Sch Software, Beijing 100190, Peoples R China

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2024年 / 21卷

关键词：

Transient analysis; Satellite images; Image color analysis; Atmospheric modeling; Image reconstruction; Remote sensing; Optical sensors; Neural radiance fields (NeRFs); photogrammetry; satellite imagery; scene reconstruction; MULTIVIEW STEREO;

D O I：

10.1109/LGRS.2023.3337352

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

We introduce a novel method tailored for unconstrained multiview optical satellite photogrammetry in time-varying illumination and reflection conditions. Our approach uses continuous radiance fields to represent surface radiance and albedo based on radiometry principles, integrating both static and transient components for satellite photogrammetry. In addition, an innovative self-supervised mechanism is introduced to optimize the learning process which leverages dark regions' accentuation, transient and static composition, and shadow regularization. Evaluations on multidate WorldView-3 images affirm that our model consistently surpasses the state-of-the-art techniques.

引用

页码：1 / 5

页数：5

共 50 条

[21] Generative Neural Articulated Radiance Fields
Bergman, Alexander W.
Kellnhofer, Petr
Wang Yifan
Chan, Eric R.
Lindell, David B.
Wetzstein, Gordon
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
[22] Hallucinated Neural Radiance Fields in the Wild
Chen, Xingyu
Zhang, Qi
Li, Xiaoyu
Chen, Yue
Feng, Ying
Wang, Xuan
Wang, Jue
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 12933 - 12942
[23] PyNeRF: Pyramidal Neural Radiance Fields
Turki, Haithem
Zollhofer, Michael
Richardt, Christian
Ramanan, Deva
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[24] Neural Radiance Fields Explode on the Scene
Dellaert, Frank
COMMUNICATIONS OF THE ACM, 2022, 65 (01) : 98 - 98
[25] Reinforcement Learning with Neural Radiance Fields
Driess, Danny
Schubert, Ingmar
Florence, Pete
Li, Yunzhu
Toussaint, Marc
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
[26] EfficientNeRF - Efficient Neural Radiance Fields
Hu, Tao
Liu, Shu
Chen, Yilun
Shen, Tiancheng
Jia, Jiaya
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 12892 - 12901
[27] Nerfies: Deformable Neural Radiance Fields
Park, Keunhong
Sinha, Utkarsh
Barron, Jonathan T.
Bouaziz, Sofien
Goldman, Dan B.
Seitz, Steven M.
Martin-Brualla, Ricardo
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 5845 - 5854
[28] Convolutional Neural Opacity Radiance Fields
Luo, Haimin
Chen, Anpei
Zhang, Qixuan
Pang, Bai
Wu, Minye
Xu, Lan
Yu, Jingyi
2021 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL PHOTOGRAPHY (ICCP), 2021,
[29] SPARSESAT-NERF: DENSE DEPTH SUPERVISED NEURAL RADIANCE FIELDS FOR SPARSE SATELLITE IMAGES
Zhang, Lulin
Rupnik, Ewelina
GEOSPATIAL WEEK 2023, VOL. 10-1, 2023, : 895 - 902
[30] SatensoRF: Fast Satellite Tensorial Radiance Field for Multidate Satellite Imagery of Large Size
Zhang, Tongtong
Zhou, Yu
Li, Yuanxiang
Wei, Xian
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 15

← 1 2 3 4 5 →