Revisiting Optical Flow Estimation in 360 Videos

Abstract

Nowadays 360 video analysis has become a significant research topic in the field since the appearance of high-quality and low-cost 360 wearable devices. In this paper, we propose a novel LiteFlowNet360 architecture for 360 videos optical flow estimation. We design LiteFlowNet360 as a domain adaptation framework from perspective video domain to 360 video domain. We adapt it from simple kernel transformation techniques inspired by Kernel Transformer Network (KTN) to cope with inherent distortion in 360 videos caused by the sphere-to-plane projection. First, we apply an incremental transformation of convolution layers in feature pyramid network and show that further transformation in inference and regularization layers are not important, hence reducing the network growth in terms of size and computation cost. Second, we refine the network by training with augmented data in a supervised manner. We perform data augmentation by projecting the images in a sphere and re-projecting to a plane. Third, we train LiteFlowNet360 in a self-supervised manner using target domain 360 videos. Experimental results show the promising results of 360 video optical flow estimation using the proposed novel architecture.

arXiv comment8 Pages, 7 figures, 1 Table, 5 Equations, 25th International Conference on Pattern Recognition Milan, Italy

References in corpus (6)

• FlowNet: Learning Optical Flow with Convolutional Networks
• Learning Spherical Convolution for Fast Features from 360° Imagery
• Learning to Extract Motion from Videos in Convolutional Neural Networks
• Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness
• Kernel Transformer Networks for Compact Spherical Convolution
• Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos