A survey of variational and CNN-based optical flow techniques

Zhigang Tu, Wei Xie, Dejun Zhang, Ronald Poppe, Remco C. Veltkamp, Baoxin Li, Junsong Yuan

Research output: Contribution to journalArticlepeer-review

111 Scopus citations


Dense motion estimations obtained from optical flow techniques play a significant role in many image processing and computer vision tasks. Remarkable progress has been made in both theory and its application in practice. In this paper, we provide a systematic review of recent optical flow techniques with a focus on the variational method and approaches based on Convolutional Neural Networks (CNNs). These two categories have led to state-of-the-art performance. We discuss recent modifications and extensions of the original model, and highlight remaining challenges. For the first time, we provide an overview of recent CNN-based optical flow methods and discuss their potential and current limitations.

Original languageEnglish (US)
Pages (from-to)9-24
Number of pages16
JournalSignal Processing: Image Communication
StatePublished - Mar 2019


  • CNN-based method
  • Challenges
  • Evaluation measures
  • Optical flow
  • Variational method

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering


Dive into the research topics of 'A survey of variational and CNN-based optical flow techniques'. Together they form a unique fingerprint.

Cite this