Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation

Hugo Germain
  • Fonction : Auteur
  • PersonId : 1120520
Guillaume Bourmaud
  • Fonction : Auteur
  • PersonId : 1120521

Résumé

Absolute camera pose estimation is usually addressed by sequentially solving two distinct subproblems: First a feature matching problem that seeks to establish putative 2D-3D correspondences, and then a Perspective-n-Point problem that minimizes, w.r.t. the camera pose, the sum of socalled Reprojection Errors (RE). We argue that generating putative 2D-3D correspondences 1) leads to an important loss of information that needs to be compensated as far as possible, within RE, through the choice of a robust loss and the tuning of its hyperparameters and 2) may lead to an RE that conveys erroneous data to the pose estimator. In this paper, we introduce the Neural Reprojection Error (NRE) as a substitute for RE. NRE allows to rethink the camera pose estimation problem by merging it with the feature learning problem, hence leveraging richer information than 2D-3D correspondences and eliminating the need for choosing a robust loss and its hyperparameters. Thus NRE can be used as training loss to learn image descriptors tailored for pose estimation. We also propose a coarse-to-fine optimization method able to very efficiently minimize a sum of NRE terms w.r.t. the camera pose. We experimentally demonstrate that NRE is a good substitute for RE as it significantly improves both the robustness and the accuracy of the camera pose estimate while being computationally and memory highly efficient. From a broader point of view, we believe this new way of merging deep learning and 3D geometry may be useful in other computer vision applications. Source code and model weights will be made available at hugogermain.com/nre.
Fichier principal
Vignette du fichier
germain_cvpr21.pdf (3.37 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03482286 , version 1 (15-12-2021)

Identifiants

  • HAL Id : hal-03482286 , version 1

Citer

Hugo Germain, Vincent Lepetit, Guillaume Bourmaud. Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation. Conference on Computer Vision and Pattern Recognition, Jun 2021, Online, United States. ⟨hal-03482286⟩
17 Consultations
59 Téléchargements

Partager

Gmail Facebook X LinkedIn More