 |
 |
Article dans une revue
Corners for Layout: End-to-End Layout Recovery from 360 Images
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 for 3D layout recovery on 360 images. Our experimental results show that we outperform the state of the art relaxing assumptions about the scene and at a lower cost. We also show that our model generalizes better to camera position variations than conventional approaches by using EquiConvs, a type of convolution applied directly on the sphere projection and hence invariant to the equirectangular distortions. CFL Webpage: https://cfernandezlab.github.io/CFL/
https://hal-univ-bourgogne.archives-ouvertes.fr/hal-02140693
Contributeur : Imvia - Université de Bourgogne <>
Soumis le : lundi 27 mai 2019 - 14:52:28
Dernière modification le : mercredi 27 mai 2020 - 21:33:16
Contributeur : Imvia - Université de Bourgogne <>
Soumis le : lundi 27 mai 2019 - 14:52:28
Dernière modification le : mercredi 27 mai 2020 - 21:33:16
Lien texte intégral
