This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Fast Optical Flow using Dense Inverse Search

Till Kroeger and Radu Timofte and Dengxin Dai and Luc Van Gool
14th European Conference on Computer Vision (ECCV 2016)
September 2016


Most recent works in optical flow extraction focus on the accuracy and neglect the time complexity. However, in real-life visual applications, such as tracking, activity detection and recognition, the time complexity is critical. We propose a solution with very low time complexity and competitive accuracy for the computation of dense optical flow. It consists of three parts: 1) inverse search for patch correspondences; 2) dense displacement field creation through patch aggregation along multiple scales; 3) variational refinement. At the core of our Dense Inverse Search-based method (DIS) is the efficient search of correspondences inspired by the inverse compositional image alignment proposed by Baker and Matthews. DIS is competitive on standard optical flow benchmarks. DIS runs at 300Hz up to 600Hz on a single CPU core, reaching the temporal resolution of human’s biological vision system. It is order(s) of magnitude faster than state-of-the-art methods in the same range of accuracy, making DIS ideal for real-time applications.

Link to publisher's page
Download in pdf format
  author = {Till Kroeger and Radu Timofte and Dengxin Dai and Luc Van Gool},
  title = {Fast Optical Flow using Dense Inverse Search},
  booktitle = {14th European Conference on Computer Vision (ECCV 2016)},
  year = {2016},
  month = {September},
  pages = {471-488},
  volume = {9908},
  series = {Lecture Notes in Computer Science},
  publisher = {Springer},
  keywords = {}