English

Secrets in Computing Optical Flow by Convolutional Networks

Computer Vision and Pattern Recognition 2017-10-05 v1

Abstract

Convolutional neural networks (CNNs) have been widely used over many areas in compute vision. Especially in classification. Recently, FlowNet and several works on opti- cal estimation using CNNs shows the potential ability of CNNs in doing per-pixel regression. We proposed several CNNs network architectures that can estimate optical flow, and fully unveiled the intrinsic different between these structures.

Keywords

Cite

@article{arxiv.1710.01462,
  title  = {Secrets in Computing Optical Flow by Convolutional Networks},
  author = {Junxuan Li},
  journal= {arXiv preprint arXiv:1710.01462},
  year   = {2017}
}
R2 v1 2026-06-22T22:03:11.440Z