360deg Optical Flow using Tangent Images

Omnidirectional 360deg images have found many promising and exciting applications in computer vision, robotics and other fields, thanks to their increasing affordability, portability and their 360deg field of view. The most common format for storing, processing and visualising 360deg images is equirectangular projection (ERP). However, the distortion introduced by the nonlinear mapping from 360deg image to ERP image is still a barrier that holds back ERP images from being used as easily as conventional perspective images. This is especially relevant when estimating 360deg optical flow, as the distortions need to be mitigated appropriately. In this paper, we propose a 360deg optical flow method based on tangent images. Our method leverages gnomonic projection to locally convert ERP images to perspective images, and uniformly samples the ERP image by projection to a cubemap and regular icosahedron vertices, to incrementally refine the estimated 360deg flow fields even in the presence of large rotations. Our experiments demonstrate the benefits of our proposed method both quantitatively and qualitatively.