6533b7d7fe1ef96bd1267b1b
RESEARCH PRODUCT
OmniFlowNet: a Perspective Neural Network Adaptation for Optical Flow Estimation in Omnidirectional Images
Charles-olivier ArtizzuGuillaume AllibertCédric DemonceauxHaozhou Zhangsubject
Artificial neural networkComputer sciencebusiness.industryDistortion (optics)Perspective (graphical)[INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO]ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processing02 engineering and technology010501 environmental sciences01 natural sciencesConvolutional neural networkConvolutionOptical flow estimation0202 electrical engineering electronic engineering information engineering[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]020201 artificial intelligence & image processingComputer visionArtificial intelligencebusinessProjection (set theory)0105 earth and related environmental sciencesdescription
International audience; 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.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2021-01-10 |