Geometric Camera Pose Refinement With Learned Depth Maps - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Geometric Camera Pose Refinement With Learned Depth Maps

Résumé

We present a new method for image-only camera relocalisation composed of a fast image indexing retrieval step followed by pose refinement based on ICP (Iterative Closest Point). The first step aims to find an initial pose for the query by evaluating images similarity with low dimensional global deep descriptors. Subsequently, we predict with a fully convolutional deep encoder-decoder neural network a dense depth map from the image query. We use this depth map to create a local point cloud and refine the initial query pose using an ICP algorithm. We demonstrate the effectiveness of our new approach on various indoor scenes. Compared to learned pose regression methods, our proposal can be used on multiple scenes without the need of a specific weights-setup for each scene, while showing equivalent results.
Fichier principal
Vignette du fichier
ICIP_2019-5.pdf (414.23 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02123899 , version 1 (09-05-2019)

Identifiants

Citer

Nathan Piasco, Désiré Sidibé, Cédric Demonceaux, Valérie Gouet-Brunet. Geometric Camera Pose Refinement With Learned Depth Maps. IEEE Int. Conf. on Image Processing, Sep 2019, Taipei, Taiwan. ⟨10.1109/ICIP.2019.8803014⟩. ⟨hal-02123899⟩
150 Consultations
478 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More