Corners for Layout: End-to-End Layout Recovery from 360 Images
This addresses the problem of real-time 3D layout recovery for applications like robot navigation and AR/VR, offering an incremental improvement over existing methods.
The paper tackles 3D layout recovery from 360 images by introducing CFL, an end-to-end model that outperforms state-of-the-art methods by relaxing scene assumptions and reducing computational cost, with results showing better generalization to camera position variations.
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/