Layouts From Panoramic Images With Geometry and Deep Learning | IEEE Journals & Magazine | IEEE Xplore

Layouts From Panoramic Images With Geometry and Deep Learning


Abstract:

In this letter, we propose a novel procedure for three-dimensional layout recovery of indoor scenes from single 360° panoramic images. With such images, all scene is seen...Show More

Abstract:

In this letter, we propose a novel procedure for three-dimensional layout recovery of indoor scenes from single 360° panoramic images. With such images, all scene is seen at once, allowing us to recover closed geometries. Our method combines strategically the accuracy provided by geometric reasoning (lines and vanishing points) with the higher level of data abstraction and pattern recognition achieved by deep learning techniques (edge and normal maps). Thus, we extract structural corners from which we generate layout hypotheses of the room assuming Manhattan world. The best layout model is selected, achieving good performance on both simple rooms (box-type), and complex shaped rooms (with more than four walls). Experiments of the proposed approach are conducted within two public datasets, SUN360 and Stanford (2D-3D-S) demonstrating the advantages of estimating layouts by combining geometry and deep learning and the effectiveness of our proposal with respect to the state of the art.
Published in: IEEE Robotics and Automation Letters ( Volume: 3, Issue: 4, October 2018)
Page(s): 3153 - 3160
Date of Publication: 25 June 2018

ISSN Information:

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.