Header logo is ps

Optical Flow Estimation with Channel Constancy


Conference Paper


Large motions remain a challenge for current optical flow algorithms. Traditionally, large motions are addressed using multi-resolution representations like Gaussian pyramids. To deal with large displacements, many pyramid levels are needed and, if an object is small, it may be invisible at the highest levels. To address this we decompose images using a channel representation (CR) and replace the standard brightness constancy assumption with a descriptor constancy assumption. CRs can be seen as an over-segmentation of the scene into layers based on some image feature. If the appearance of a foreground object differs from the background then its descriptor will be different and they will be represented in different layers.We create a pyramid by smoothing these layers, without mixing foreground and background or losing small objects. Our method estimates more accurate flow than the baseline on the MPI-Sintel benchmark, especially for fast motions and near motion boundaries.

Author(s): Laura Sevilla-Lara and Deqing Sun and Erik G. Learned-Miller and Michael J. Black
Book Title: Computer Vision – ECCV 2014
Volume: 8689
Pages: 423--438
Year: 2014
Month: September

Series: Lecture Notes in Computer Science
Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars
Publisher: Springer International Publishing

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1007/978-3-319-10590-1_28
Event Name: 13th European Conference on Computer Vision
Event Place: Zürich, Switzerland

Links: pdf


  title = {Optical Flow Estimation with Channel Constancy},
  author = {Sevilla-Lara, Laura and Sun, Deqing and Learned-Miller, Erik G. and Black, Michael J.},
  booktitle = {Computer Vision -- ECCV 2014},
  volume = {8689},
  pages = {423--438},
  series = {Lecture Notes in Computer Science},
  editors = {D. Fleet  and T. Pajdla and B. Schiele  and T. Tuytelaars },
  publisher = {Springer International Publishing},
  month = sep,
  year = {2014},
  month_numeric = {9}