Optical Flow Estimation with Channel Constancy

Laura Sevilla-Lara, Deqing Sun, Erik G. Learned-Miller, Michael J. Black

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationComputer Vision - ECCV 2014
EditorsDavid Fleet, Tomas Pajdla, Bernt Schiele, Tinne Tuytelaars
Place of PublicationCham
PublisherSpringer
Pages423-438
Number of pages16
ISBN (Print)978-3-319-10590-1
Publication statusPublished - 2014
EventEuropean Conference on Computer Vision 2014 - Zurich, Switzerland
Duration: 5 Sept 201412 Sept 2014

Conference

ConferenceEuropean Conference on Computer Vision 2014
Abbreviated titleECCV 2014
Country/TerritorySwitzerland
CityZurich
Period5/09/1412/09/14

Fingerprint

Dive into the research topics of 'Optical Flow Estimation with Channel Constancy'. Together they form a unique fingerprint.

Cite this