EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer

Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov, Xiaotian Li, Yi Zhao, Giorgos Tolias, Juho Kannala

International Journal of Computer Vision · 2024-07 · 132 (7) · 2530-2550

DOI: 10.1007/s11263-023-01982-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 06.02.2024. Verfasst von Shuzhe Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Academic of Finland, Junior Star GACR, Programme Johannes Amos Comenius.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model. Recently, deep neural networks have been exploited to regress the mapping between raw pixels and 3D coordinates in the scene, and thus the matching is implicitly performed by the forward pass through the network. However, in a large and ambiguous environment, learning such a regression task directly can be difficult for a single network. In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image. The proposed method, which is an extension of HSCNet, allows us to train compact models which scale robustly to large environments. It sets a new state-of-the-art for single-image localization on the 7-Scenes, 12-Scenes, Cambridge Landmarks datasets, and the combined indoor scenes.

Förderung

  • Academic of Finland
  • Junior Star GACR
  • Programme Johannes Amos Comenius

Zitieren

APA

Wang, S., Laskar, Z., Melekhov, I., Li, X., Zhao, Y., Tolias, G., & Kannala, J. (2024). HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer. International Journal of Computer Vision, 132(7), 2530-2550. https://doi.org/10.1007/s11263-023-01982-9

Vancouver

Wang S, Laskar Z, Melekhov I, Li X, Zhao Y, Tolias G, et al. HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer. International Journal of Computer Vision. 2024;132(7):2530-2550. doi:10.1007/s11263-023-01982-9

BibTeX
@article{Wang2024,
  author = {Wang, Shuzhe and Laskar, Zakaria and Melekhov, Iaroslav and Li, Xiaotian and Zhao, Yi and Tolias, Giorgos and Kannala, Juho},
  title = {HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer},
  journal = {International Journal of Computer Vision},
  year = {2024},
  volume = {132},
  number = {7},
  pages = {2530--2550},
  doi = {10.1007/s11263-023-01982-9}
}
Kostenlos starten →