Skip to Main content Skip to Navigation
Conference papers

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

Abstract : 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 1 and several equirectangular videos realized from real indoor and outdoor scenes, OmniFlowNet shows better performance than its original network without extra training.
Document type :
Conference papers
Complete list of metadata

Cited literature [23 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02968191
Contributor : Guillaume Allibert Connect in order to contact the contributor
Submitted on : Thursday, October 15, 2020 - 2:47:59 PM
Last modification on : Wednesday, October 13, 2021 - 3:39:05 AM

File

ICPR_2020_FINAL.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02968191, version 1

Citation

Charles-Olivier Artizzu, Haozhou Zhang, Guillaume Allibert, Cédric Demonceaux. OmniFlowNet: a Perspective Neural Network Adaptation for Optical Flow Estimation in Omnidirectional Images. 25th International Conference on Pattern Recognition (ICPR), Jan 2021, Milan, Italy. ⟨hal-02968191⟩

Share

Metrics

Record views

238

Files downloads

454