SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360deg Images

Yeonkun Lee, Jaeseok Jeong, Jongseob Yun, Wonjune Cho, Kuk-Jin Yoon; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 9181-9189

Abstract


Omni-directional cameras have many advantages overconventional cameras in that they have a much wider field-of-view (FOV). Accordingly, several approaches have beenproposed recently to apply convolutional neural networks(CNNs) to omni-directional images for various visual tasks.However, most of them use image representations defined inthe Euclidean space after transforming the omni-directionalviews originally formed in the non-Euclidean space. Thistransformation leads to shape distortion due to nonuniformspatial resolving power and the loss of continuity. Theseeffects make existing convolution kernels experience diffi-culties in extracting meaningful information. This paper presents a novel method to resolve such prob-lems of applying CNNs to omni-directional images. Theproposed method utilizes a spherical polyhedron to rep-resent omni-directional views. This method minimizes thevariance of the spatial resolving power on the sphere sur-face, and includes new convolution and pooling methodsfor the proposed representation. The proposed method canalso be adopted by any existing CNN-based methods. Thefeasibility of the proposed method is demonstrated throughclassification, detection, and semantic segmentation taskswith synthetic and real datasets.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Lee_2019_CVPR,
author = {Lee, Yeonkun and Jeong, Jaeseok and Yun, Jongseob and Cho, Wonjune and Yoon, Kuk-Jin},
title = {SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360deg Images},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}