OmniFlowNet: a Perspective Neural Network Adaptation for Optical Flow Estimation in Omnidirectional Images - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

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

Résumé

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.
Fichier principal
Vignette du fichier
ICPR_2020_FINAL.pdf (10.12 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02968191 , version 1 (15-10-2020)

Identifiants

  • HAL Id : hal-02968191 , version 1

Citer

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⟩
308 Consultations
134 Téléchargements

Partager

Gmail Facebook X LinkedIn More