Layouts from Panoramic Images with Geometry and Deep Learning
This work addresses indoor scene reconstruction for applications like robotics or VR, but it is incremental as it builds on existing Manhattan world assumptions and combines known techniques.
The paper tackles 3D layout recovery from single panoramic images by combining geometric reasoning and deep learning to extract structural corners and generate layout hypotheses, achieving good performance on both simple and complex rooms as demonstrated on SUN360 and Stanford datasets.
In this paper, we propose a novel procedure for 3D layout recovery of indoor scenes from single 360 degrees panoramic images. With such images, all scene is seen at once, allowing 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.