Normalized convolution upsampling for refined optical flow estimation

Abdelrahman Eldesokey, Michael Felsberg

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish (US)
Title of host publicationVISAPP
EditorsGiovanni Maria Farinella, Petia Radeva, Jose Braz, Kadi Bouatouch
PublisherSciTePress
Pages742-752
Number of pages11
ISBN (Electronic)9789897584886
StatePublished - 2021
Event16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2021 - Virtual, Online
Duration: Feb 8 2021Feb 10 2021

Publication series

NameVISIGRAPP 2021 - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume5

Conference

Conference16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2021
CityVirtual, Online
Period02/8/2102/10/21

Keywords

  • Joint image upsampling
  • Normalized convolution
  • Optical flow estimation CNNs
  • Spare CNNS

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Normalized convolution upsampling for refined optical flow estimation'. Together they form a unique fingerprint.

Cite this