NeRFOrtho: Orthographic Projection Images Generation based on Neural Radiance Fields

The application value of orthographic projection images is substantial, especially in the field of remote sensing for True Digital Orthophoto Map (TDOM) generation. Existing methods for orthographic projection image generation primarily involve geometric correction or explicit projection of photogra...

Full description

Saved in:
Bibliographic Details
Main Authors: Dongdong Yue, Xinyi Liu, Yi Wan, Yongjun Zhang, Maoteng Zheng, Weiwei Fan, Jiachen Zhong
Format: Article
Language:English
Published: Elsevier 2025-02-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843225000251
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850189644267782144
author Dongdong Yue
Xinyi Liu
Yi Wan
Yongjun Zhang
Maoteng Zheng
Weiwei Fan
Jiachen Zhong
author_facet Dongdong Yue
Xinyi Liu
Yi Wan
Yongjun Zhang
Maoteng Zheng
Weiwei Fan
Jiachen Zhong
author_sort Dongdong Yue
collection DOAJ
description The application value of orthographic projection images is substantial, especially in the field of remote sensing for True Digital Orthophoto Map (TDOM) generation. Existing methods for orthographic projection image generation primarily involve geometric correction or explicit projection of photogrammetric mesh models. However, the former suffers from projection differences and stitching lines, while the latter is plagued by poor model quality and high costs. This paper presents NeRFOrtho, a new method for generating orthographic projection images from neural radiance fields at arbitrary angles. By constructing Neural Radiance Fields from multi-view images with known viewpoints and positions, the projection method is altered to render orthographic projection images on a plane where projection rays are parallel to each other. In comparison to existing orthographic projection image generation methods, this approach produces orthographic projection images devoid of projection differences and distortions, while offering superior texture details and higher precision. We also show the applicative potential of the method when rendering TDOM and the texture of building façade.
format Article
id doaj-art-4daede7236f64045bf08a55c8fdaba10
institution OA Journals
issn 1569-8432
language English
publishDate 2025-02-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-4daede7236f64045bf08a55c8fdaba102025-08-20T02:15:33ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-02-0113610437810.1016/j.jag.2025.104378NeRFOrtho: Orthographic Projection Images Generation based on Neural Radiance FieldsDongdong Yue0Xinyi Liu1Yi Wan2Yongjun Zhang3Maoteng Zheng4Weiwei Fan5Jiachen Zhong6School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, HB 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, HB 430079, China; Corresponding authors.School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, HB 430079, China; Corresponding authors.School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, HB 430079, ChinaNational Engineering Research Center for Geographic Information System, China University of Geosciences (Wuhan), Wuhan, HB 430078 ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, HB 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, HB 430079, ChinaThe application value of orthographic projection images is substantial, especially in the field of remote sensing for True Digital Orthophoto Map (TDOM) generation. Existing methods for orthographic projection image generation primarily involve geometric correction or explicit projection of photogrammetric mesh models. However, the former suffers from projection differences and stitching lines, while the latter is plagued by poor model quality and high costs. This paper presents NeRFOrtho, a new method for generating orthographic projection images from neural radiance fields at arbitrary angles. By constructing Neural Radiance Fields from multi-view images with known viewpoints and positions, the projection method is altered to render orthographic projection images on a plane where projection rays are parallel to each other. In comparison to existing orthographic projection image generation methods, this approach produces orthographic projection images devoid of projection differences and distortions, while offering superior texture details and higher precision. We also show the applicative potential of the method when rendering TDOM and the texture of building façade.http://www.sciencedirect.com/science/article/pii/S1569843225000251Multi-view ImagesNeural Radiation FieldsOrthographic ProjectionTrue Orthophoto
spellingShingle Dongdong Yue
Xinyi Liu
Yi Wan
Yongjun Zhang
Maoteng Zheng
Weiwei Fan
Jiachen Zhong
NeRFOrtho: Orthographic Projection Images Generation based on Neural Radiance Fields
International Journal of Applied Earth Observations and Geoinformation
Multi-view Images
Neural Radiation Fields
Orthographic Projection
True Orthophoto
title NeRFOrtho: Orthographic Projection Images Generation based on Neural Radiance Fields
title_full NeRFOrtho: Orthographic Projection Images Generation based on Neural Radiance Fields
title_fullStr NeRFOrtho: Orthographic Projection Images Generation based on Neural Radiance Fields
title_full_unstemmed NeRFOrtho: Orthographic Projection Images Generation based on Neural Radiance Fields
title_short NeRFOrtho: Orthographic Projection Images Generation based on Neural Radiance Fields
title_sort nerfortho orthographic projection images generation based on neural radiance fields
topic Multi-view Images
Neural Radiation Fields
Orthographic Projection
True Orthophoto
url http://www.sciencedirect.com/science/article/pii/S1569843225000251
work_keys_str_mv AT dongdongyue nerforthoorthographicprojectionimagesgenerationbasedonneuralradiancefields
AT xinyiliu nerforthoorthographicprojectionimagesgenerationbasedonneuralradiancefields
AT yiwan nerforthoorthographicprojectionimagesgenerationbasedonneuralradiancefields
AT yongjunzhang nerforthoorthographicprojectionimagesgenerationbasedonneuralradiancefields
AT maotengzheng nerforthoorthographicprojectionimagesgenerationbasedonneuralradiancefields
AT weiweifan nerforthoorthographicprojectionimagesgenerationbasedonneuralradiancefields
AT jiachenzhong nerforthoorthographicprojectionimagesgenerationbasedonneuralradiancefields