Sat-Mesh: Learning Neural Implicit Surfaces for Multi-View Satellite Reconstruction
Automatic reconstruction of surfaces from satellite imagery is a hot topic in computer vision and photogrammetry. State-of-the-art reconstruction methods typically produce 2.5D elevation data. In contrast, we propose a one-stage method directly generating a 3D mesh model from multi-view satellite im...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/17/4297 |
| _version_ | 1797581946932428800 |
|---|---|
| author | Yingjie Qu Fei Deng |
| author_facet | Yingjie Qu Fei Deng |
| author_sort | Yingjie Qu |
| collection | DOAJ |
| description | Automatic reconstruction of surfaces from satellite imagery is a hot topic in computer vision and photogrammetry. State-of-the-art reconstruction methods typically produce 2.5D elevation data. In contrast, we propose a one-stage method directly generating a 3D mesh model from multi-view satellite imagery. We introduce a novel Sat-Mesh approach for satellite implicit surface reconstruction: We represent the scene as a continuous signed distance function (SDF) and leverage a volume rendering framework to learn the SDF values. To address the challenges posed by lighting variations and inconsistent appearances in satellite imagery, we incorporate a latent vector in the network architecture to encode image appearances. Furthermore, we introduce a multi-view stereo constraint to enhance surface quality. This constraint minimizes the similarity between image patches to optimize the position and orientation of the SDF surface. Experimental results demonstrate that our method achieves superior visual quality and quantitative accuracy in generating mesh models. Moreover, our approach can learn seasonal variations in satellite imagery, resulting in texture mesh models with different and consistent seasonal appearances. |
| first_indexed | 2024-03-10T23:13:54Z |
| format | Article |
| id | doaj.art-e8ccea553c4142008ccf99e5150dfbc6 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:13:54Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-e8ccea553c4142008ccf99e5150dfbc62023-11-19T08:47:13ZengMDPI AGRemote Sensing2072-42922023-08-011517429710.3390/rs15174297Sat-Mesh: Learning Neural Implicit Surfaces for Multi-View Satellite ReconstructionYingjie Qu0Fei Deng1School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan 430079, ChinaAutomatic reconstruction of surfaces from satellite imagery is a hot topic in computer vision and photogrammetry. State-of-the-art reconstruction methods typically produce 2.5D elevation data. In contrast, we propose a one-stage method directly generating a 3D mesh model from multi-view satellite imagery. We introduce a novel Sat-Mesh approach for satellite implicit surface reconstruction: We represent the scene as a continuous signed distance function (SDF) and leverage a volume rendering framework to learn the SDF values. To address the challenges posed by lighting variations and inconsistent appearances in satellite imagery, we incorporate a latent vector in the network architecture to encode image appearances. Furthermore, we introduce a multi-view stereo constraint to enhance surface quality. This constraint minimizes the similarity between image patches to optimize the position and orientation of the SDF surface. Experimental results demonstrate that our method achieves superior visual quality and quantitative accuracy in generating mesh models. Moreover, our approach can learn seasonal variations in satellite imagery, resulting in texture mesh models with different and consistent seasonal appearances.https://www.mdpi.com/2072-4292/15/17/4297satellite 3D reconstructionphotogrammetryneural radiance fieldsneural implicit surfacesnormalized cross-correlationlatent appearance |
| spellingShingle | Yingjie Qu Fei Deng Sat-Mesh: Learning Neural Implicit Surfaces for Multi-View Satellite Reconstruction Remote Sensing satellite 3D reconstruction photogrammetry neural radiance fields neural implicit surfaces normalized cross-correlation latent appearance |
| title | Sat-Mesh: Learning Neural Implicit Surfaces for Multi-View Satellite Reconstruction |
| title_full | Sat-Mesh: Learning Neural Implicit Surfaces for Multi-View Satellite Reconstruction |
| title_fullStr | Sat-Mesh: Learning Neural Implicit Surfaces for Multi-View Satellite Reconstruction |
| title_full_unstemmed | Sat-Mesh: Learning Neural Implicit Surfaces for Multi-View Satellite Reconstruction |
| title_short | Sat-Mesh: Learning Neural Implicit Surfaces for Multi-View Satellite Reconstruction |
| title_sort | sat mesh learning neural implicit surfaces for multi view satellite reconstruction |
| topic | satellite 3D reconstruction photogrammetry neural radiance fields neural implicit surfaces normalized cross-correlation latent appearance |
| url | https://www.mdpi.com/2072-4292/15/17/4297 |
| work_keys_str_mv | AT yingjiequ satmeshlearningneuralimplicitsurfacesformultiviewsatellitereconstruction AT feideng satmeshlearningneuralimplicitsurfacesformultiviewsatellitereconstruction |