ImPosing: Implicit Pose Encoding for Efficient Visual Localization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

ImPosing: Implicit Pose Encoding for Efficient Visual Localization

Arthur Moreau
  • Fonction : Auteur
  • PersonId : 1122704
Nathan Piasco
Dzmitry Tsishkou
  • Fonction : Auteur
  • PersonId : 1135713
Bogdan Stanciulescu
Arnaud de La Fortelle

Résumé

We propose a novel learning-based formulation for visual localization of vehicles that can operate in real-time in city-scale environments. Visual localization algorithms determine the position and orientation from which an image has been captured, using a set of geo-referenced images or a 3D scene representation. Our new localization paradigm, named Implicit Pose Encoding (ImPosing), embeds images and camera poses into a common latent representation with 2 separate neural networks, such that we can compute a similarity score for each image-pose pair. By evaluating candidates through the latent space in a hierarchical manner, the camera position and orientation are not directly regressed but incrementally refined. Very large environments force competitors to store gigabytes of map data, whereas our method is very compact independently of the reference database size. In this paper, we describe how to effectively optimize our learned modules, how to combine them to achieve real-time localization, and demonstrate results on diverse large scale scenarios that significantly outperform prior work in accuracy and computational efficiency.
Fichier principal
Vignette du fichier
ImPosing_cameraready.pdf (1.22 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03886744 , version 1 (06-12-2022)

Identifiants

  • HAL Id : hal-03886744 , version 1

Citer

Arthur Moreau, Thomas Gilles, Nathan Piasco, Dzmitry Tsishkou, Bogdan Stanciulescu, et al.. ImPosing: Implicit Pose Encoding for Efficient Visual Localization. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023 ), Jan 2023, Waikoloa Village, United States. ⟨hal-03886744⟩
15 Consultations
26 Téléchargements

Partager

Gmail Facebook X LinkedIn More