Accéder directement au contenu Accéder directement à la navigation
Article dans une revue

Corners for Layout: End-to-End Layout Recovery From 360 Images

Clara Fernandez-Labrador 1, * José Fácil 1, * Alejandro Perez-Yus 1, * Cédric Demonceaux 2 Javier Civera 1, * Jose Guerrero 1, *
* Auteur correspondant
2 VIBOT - Equipe VIBOT - VIsion pour la roBOTique [ImViA EA7535 - ERL CNRS 6000]
CNRS - Centre National de la Recherche Scientifique : ERL 6000, ImViA - Imagerie et Vision Artificielle [Dijon]
Abstract : The problem of 3D layout recovery in indoor scenes has been a core research topic for over a decade. However, there are still several major challenges that remain unsolved. Among the most relevant ones, a major part of the state-of-the-art methods make implicit or explicit assumptions on the scenes ;e.g. box-shaped or Manhattan layouts. Also, current methods are computationally expensive and not suitable for real-time applications like robot navigation and AR/VR. In this work we present CFL (Corners for Layout), the first end-to-end model that predicts layout corners for 3D layout recovery on images. Our experimental results show that we outperform the state of the art, making less assumptions on the scene than other works, and with lower cost. We also show that our model generalizes better to camera position variations than conventional approaches by using EquiConvs, a convolution applied directly on the spherical projection and hence invariant to the equirectangular distortions.
Type de document :
Article dans une revue
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-02566981
Contributeur : Imvia - Université de Bourgogne <>
Soumis le : jeudi 7 mai 2020 - 15:22:10
Dernière modification le : vendredi 8 mai 2020 - 01:38:24

Lien texte intégral

Identifiants

Collections

Citation

Clara Fernandez-Labrador, José Fácil, Alejandro Perez-Yus, Cédric Demonceaux, Javier Civera, et al.. Corners for Layout: End-to-End Layout Recovery From 360 Images. IEEE Robotics and Automation Letters, IEEE 2020, 5 (2), pp.1255-1262. ⟨10.1109/LRA.2020.2967274⟩. ⟨hal-02566981⟩

Partager

Métriques

Consultations de la notice

39