%0 Journal Article %T Corners for Layout: End-to-End Layout Recovery From 360 Images %+ Aragón Institute of Engineering Research [Zaragoza] (I3A) %+ Equipe VIBOT - VIsion pour la roBOTique [ImViA EA7535 - ERL CNRS 6000] (VIBOT) %A Fernandez-Labrador, Clara %A Fácil, José, M %A Perez-Yus, Alejandro %A Demonceaux, Cédric %A Civera, Javier %A Guerrero, Jose, J %Z Spanish GovernmentRTI2018-096903-B-I00PGC2018-096367-B-I00 %Z Gobierno de AragonGrupo DGA-T45 17R/FSE %Z Region Bourgogne-Franche-Comte2017-9201AAO048S01342 %< avec comité de lecture %@ 2377-3766 %J IEEE Robotics and Automation Letters %I IEEE %V 5 %N 2 %P 1255-1262 %8 2020-04 %D 2020 %R 10.1109/LRA.2020.2967274 %K Omnidirectional vision %K semantic scene understanding %Z Computer Science [cs]/Robotics [cs.RO]Journal articles %X 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. %G English %L hal-02566981 %U https://u-bourgogne.hal.science/hal-02566981 %~ UNIV-BOURGOGNE %~ CNRS %~ IMVIA %~ VIBOT