Paper Info
Title
360° Surface Regression with a Hyper-Sphere Loss
Abstract
Omnidirectional vision is becoming increasingly relevant as more efficient 360° image acquisition is now possible. However, the lack of annotated 360° datasets has hindered the application of deep learning techniques on spherical content. This is further exaggerated on tasks where ground truth acquisition is difficult, such as monocular surface estimation. While recent research approaches on the 2D domain overcome this challenge by relying on generating normals from depth cues using RGB-D sensors, this is very difficult to apply on the spherical domain. In this work, we address the unavailability of sufficient 360° ground truth normal data, by leveraging existing 3D datasets and remodelling them via rendering. We present a dataset of 360° images of indoor spaces with their corresponding ground truth surface normal, and train a deep convolutional neural network (CNN) on the task of monocular 360° surface estimation. We achieve this by minimizing a novel angular loss function defined on the hyper-sphere using simple quaternion algebra. We put an effort to appropriately compare with other state of the art methods trained on planar datasets and finally, present the practical applicability of our trained model on a spherical image re-lighting task using completely unseen data by qualitatively showing the promising generalization ability of our dataset and model.
Year
DOI
Venue
2019
10.1109/3DV.2019.00037
2019 International Conference on 3D Vision (3DV)
Keywords
DocType
ISSN
omnidirectional,spherical panorama,surface regression,surface normals,deep learning,360°,quaternion,360° dataset,indoor scenes dataset,cnn,deep neural networks,hypersphere
Conference
2378-3826
ISBN
Citations 
PageRank 
978-1-7281-3132-0
0
0.34
References 
Authors
20
7
Name
Order
Citations
PageRank
Antonios Karakottas100.34
Nikolaos Zioulis23410.15
Stamatis Samaras300.34
Dimitrios Ataloglou451.93
Vasileios Gkitsas501.01
Dimitrios Zarpalas630333.96
Petros Daras71129131.72