EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Georecon: a coarse-to-fine visual 3D reconstruction approach for high-resolution images with neural matching priors

Weijia Bei, Xiangtao Fan, Hongdeng Jian, Xiaoping Du, Dongmei Yan, Jianhao Xu, Qifeng Ge

International Journal of Digital Earth · 31.12.2024 · 17 (1)

DOI: 10.1080/17538947.2024.2421956 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Digital Earth, online erschienen am 30.10.2024. Verfasst von Weijia Bei und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Key Research and Development Program of China, Director Fund of the International Research Center of Big Data for Sustainable Development Goals.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Visual 3D reconstruction enables rebuilding 3D scenes from captured images, serving as a fundamental data source for digital earth modeling and intelligent cities. In the foundational step, recent methods leverage learning-based descriptors for image registration and achieve tremendous advances in precision and robustness. However, these methods inevitably execute down sampling towards high-resolution images to fit the needs of neural networks, which leads to precision degradation of feature localization and matching. Thus, we propose GeoRecon: a novel coarse-to-fine visual 3D reconstruction method that optimally utilizes high-resolution images for high-quality visual 3D reconstruction. Firstly, the coarse stage conducts coarse reconstruction from downsampled images by performing neural matching with geometric priors. Secondly, we define the fine-grained stage, proposing a GPU-based algorithm for generating image-patch correspondences based on the neural matching priors to perform fine-grained image registration. Finally, based on the optimized camera poses under this coarse-to-fine paradigm, progressive dense reconstruction leveraging efficient neural radiance fields is proposed to accomplish the high-quality MVS reconstruction. Comparative experiments across various scenarios demonstrate the proposed method’s superior precision, robustness, and reconstruction quality.

Förderung

  • National Key Research and Development Program of China
  • Director Fund of the International Research Center of Big Data for Sustainable Development Goals

Zitieren

APA

Bei, W., Fan, X., Jian, H., Du, X., Yan, D., Xu, J., & Ge, Q. (2024). Georecon: a coarse-to-fine visual 3D reconstruction approach for high-resolution images with neural matching priors. International Journal of Digital Earth, 17(1). https://doi.org/10.1080/17538947.2024.2421956

Vancouver

Bei W, Fan X, Jian H, Du X, Yan D, Xu J, et al. Georecon: a coarse-to-fine visual 3D reconstruction approach for high-resolution images with neural matching priors. International Journal of Digital Earth. 2024;17(1). doi:10.1080/17538947.2024.2421956

BibTeX
@article{Bei2024,
  author = {Bei, Weijia and Fan, Xiangtao and Jian, Hongdeng and Du, Xiaoping and Yan, Dongmei and Xu, Jianhao and Ge, Qifeng},
  title = {Georecon: a coarse-to-fine visual 3D reconstruction approach for high-resolution images with neural matching priors},
  journal = {International Journal of Digital Earth},
  year = {2024},
  volume = {17},
  number = {1},
  doi = {10.1080/17538947.2024.2421956}
}
Kostenlos starten →