Normalized Convolution Upsampling for Refined Optical Flow Estimation

Abdelrahman Eldesokey, Michael Felsberg

Abstract

Optical flow is a regression task where convolutional neural networks (CNNs) have led to major breakthroughs. However, this comes at major computational demands due to the use of cost-volumes and pyramidal representations. This was mitigated by producing flow predictions at quarter the resolution, which are upsampled using bilinear interpolation during test time. Consequently, fine details are usually lost and post-processing is needed to restore them. We propose the Normalized Convolution UPsampler (NCUP), an efficient joint upsampling approach to produce the full-resolution flow during the training of optical flow CNNs. Our proposed approach formulates the upsampling task as a sparse problem and employs the normalized convolutional neural networks to solve it. We evaluate our upsampler against existing joint upsampling approaches when trained end-to-end with a a coarse-to-fine optical flow CNN (PWCNet) and we show that it outperforms all other approaches on the FlyingChairs dataset while having at least one order fewer parameters. Moreover, we test our upsampler with a recurrent optical flow CNN (RAFT) and we achieve state-of-the-art results on Sintel benchmark with ∼ 6% error reduction, and on-par on the KITTI dataset, while having 7.5% fewer parameters (see Figure 1). Finally, our upsampler shows better generalization capabilities than RAFT when trained and evaluated on different datasets.

Download


Paper Citation


in Harvard Style

Eldesokey A. and Felsberg M. (2021). Normalized Convolution Upsampling for Refined Optical Flow Estimation.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 742-752. DOI: 10.5220/0010343707420752


in Bibtex Style

@conference{visapp21,
author={Abdelrahman Eldesokey and Michael Felsberg},
title={Normalized Convolution Upsampling for Refined Optical Flow Estimation},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={742-752},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010343707420752},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - Normalized Convolution Upsampling for Refined Optical Flow Estimation
SN - 978-989-758-488-6
AU - Eldesokey A.
AU - Felsberg M.
PY - 2021
SP - 742
EP - 752
DO - 10.5220/0010343707420752