ML Anthology

Devon: Deformable Volume Network for Learning Optical Flow

Yao Lu, Jack Valmadre, Heng Wang, Juho Kannala, Mehrtash Harandi, Philip H. S. Torr
ECCVW 2018 pp. 673-677
doi:10.1007/978-3-030-11024-6_50 /eccvw/2018/lu2018eccvw-devon/

Abstract

We propose a new neural network module, Deformable Cost Volume, for learning large displacement optical flow. The module does not distort the original images or their feature maps and therefore avoids the artifacts associated with warping. Based on this module, a new neural network model is proposed. The full version of this paper can be found online ( https://arxiv.org/abs/1802.07351 ).

PDF ECCVW Semantic Scholar

Cite

Text

Lu et al. "Devon: Deformable Volume Network for Learning Optical Flow." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11024-6_50

Markdown

[Lu et al. "Devon: Deformable Volume Network for Learning Optical Flow." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/lu2018eccvw-devon/) doi:10.1007/978-3-030-11024-6_50

BibTeX

@inproceedings{lu2018eccvw-devon,
  title     = {{Devon: Deformable Volume Network for Learning Optical Flow}},
  author    = {Lu, Yao and Valmadre, Jack and Wang, Heng and Kannala, Juho and Harandi, Mehrtash and Torr, Philip H. S.},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {673-677},
  doi       = {10.1007/978-3-030-11024-6_50},
  url       = {https://mlanthology.org/eccvw/2018/lu2018eccvw-devon/}
}