OmniFlowNet : a Perspective Neural Network Adaptation forOptical Flow Estimation in Omnidirectional Images

Author / Creator

ICPR 2020 MAIN CONFERENCE (2021)

Conferences

ICPR 2020 MAIN CONFERENCE PS T3.1: Computer Vision and Applications-Poster (2021)

Available as

Online

Summary

Spherical cameras and the latest image processing techniques open up new horizons. In particular, methods based on Convolutional Neural Networks (CNNs) now give excellent results for optical flow e...

Spherical cameras and the latest image processing techniques open up new horizons. In particular, methods based on Convolutional Neural Networks (CNNs) now give excellent results for optical flow estimation on perspective images. However, these approaches are highly dependent on their architectures and training datasets. This paper proposes to benefit from years of improvement in perspective images optical flow estimation and to apply it to omnidirectional ones without training on new datasets. Our network, OmniFlowNet, is built on a CNN specialized in perspective images. Its convolution operation is adapted to be consistent with the equirectangular projection. Tested on spherical datasets created with Blender and several equirectangular videos realized from real indoor and outdoor scenes, OmniFlowNet shows better performance than its original network without extra training.

Show More