RPNet: an End-to-End Network for Relative Camera Pose Estimation

Sovann En 1 Alexis Lechervy 1 Frédéric Jurie 1
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : This paper addresses the task of relative camera pose estimation from raw image pixels, by means of deep neural networks. The proposed RPNet network takes pairs of images as input and directly infers the relative poses, without the need of camera intrinsic/extrinsic. While state-of-the-art systems based on SIFT + RANSAC, are able to recover the translation vector only up to scale, RPNet is trained to produce the full translation vector, in an end-to-end way. Experimental results on the Cambridge Landmark data set show very promising results regarding the recovery of the full translation vector. They also show that RPNet produces more accurate and more stable results than traditional approaches, especially for hard images (repetitive textures, textureless images, etc.). To the best of our knowledge, RPNet is the first attempt to recover full translation vectors in relative pose estimation.
Type de document :
Communication dans un congrès
European Conference on Computer Vision Workshops, Sep 2018, Munich, Germany
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01879117
Contributeur : Sovann En <>
Soumis le : samedi 22 septembre 2018 - 10:07:23
Dernière modification le : jeudi 7 février 2019 - 14:46:44
Document(s) archivé(s) le : dimanche 23 décembre 2018 - 12:42:24

Fichier

RPNet_camera_ready_version.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01879117, version 1

Citation

Sovann En, Alexis Lechervy, Frédéric Jurie. RPNet: an End-to-End Network for Relative Camera Pose Estimation. European Conference on Computer Vision Workshops, Sep 2018, Munich, Germany. 〈hal-01879117〉

Partager

Métriques

Consultations de la notice

49

Téléchargements de fichiers

201