360{\deg} Optical Flow using Tangent Images

TL;DR

This paper introduces a novel 360-degree optical flow estimation method using tangent images, which mitigates distortions from equirectangular projection by employing gnomonic projection and cubemap sampling, improving accuracy in large rotations.

Contribution

The proposed approach uniquely combines gnomonic projection and cubemap sampling to enhance 360-degree optical flow estimation, addressing distortion issues in ERP images.

Findings

Improved optical flow accuracy in 360-degree images.

Effective handling of large rotations.

Quantitative and qualitative validation of the method.

Abstract

Omnidirectional 360{\deg} images have found many promising and exciting applications in computer vision, robotics and other fields, thanks to their increasing affordability, portability and their 360{\deg} field of view. The most common format for storing, processing and visualising 360{\deg} images is equirectangular projection (ERP). However, the distortion introduced by the nonlinear mapping from 360{\deg} 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 360{\deg} optical flow, as the distortions need to be mitigated appropriately. In this paper, we propose a 360{\deg} 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 360{\deg} flow fields even in the presence of large rotations. Our experiments demonstrate the benefits of our proposed method both quantitatively and qualitatively.