Hierarchical Scene Coordinate Classification and Regression for Visual Localization - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Hierarchical Scene Coordinate Classification and Regression for Visual Localization

Xiaotian Li
  • Function : Author
Shuzhe Wang
  • Function : Author
Yi Zhao
  • Function : Author
Juho Kannala
  • Function : Author


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 network consists of a series of output layers with each of them conditioned on the previous ones. The final output layer predicts the 3D coordinates and the others produce progressively finer discrete location labels. The proposed method outperforms the baseline regression-only network and allows us to train single compact models which scale robustly to large environments. It sets a new state-of-the-art for single-image RGB localization performance on the 7-Scenes, 12-Scenes, Cambridge Landmarks datasets, and three combined scenes. Moreover, for large-scale outdoor localization on the Aachen Day-Night dataset, our approach is much more accurate than existing scene coordinate regression approaches, and reduces significantly the performance gap w.r.t. explicit feature matching approaches.
Fichier principal
Vignette du fichier
Li19Hierarchical.pdf (3.7 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02384675 , version 1 (28-11-2019)



Xiaotian Li, Shuzhe Wang, Yi Zhao, Jakob Verbeek, Juho Kannala. Hierarchical Scene Coordinate Classification and Regression for Visual Localization. CVPR 2020 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2020, Seattle, United States. pp.11980-11989, ⟨10.1109/CVPR42600.2020.01200⟩. ⟨hal-02384675⟩
424 View
457 Download



Gmail Mastodon Facebook X LinkedIn More