Interactive multicut video segmentation

  • Evgeny Levinkov
  • , James Tompkin
  • , Nicolas Bonneel
  • , Steffen Kirchhoff
  • , Bjoern Andres
  • , Hanspeter Pfister

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Video segmentation requires separating foreground from background, but the general problem extends to more complicated scene segmentations of different objects and their multiple parts. We develop a new approach to interactive multi-label video segmentation where many objects are segmented simultaneously with consistent spatio-temporal boundaries, based on intuitive multi-colored brush scribbles. From these scribbles, we derive constraints to define a combinatorial problem known as the multicut-a problem notoriously difficult and slow to solve. We describe a solution using efficient heuristics to make multi-label video segmentation interactive. As our solution generalizes typical binary segmentation tasks, while also improving efficiency in multi-label tasks, our work shows the promise of multicuts for interactive video segmentation.

Original languageEnglish
Title of host publicationPacific Graphics 2016 - 24th Pacific Conference on Computer Graphics and Applications, Short Papers Proceedings
EditorsEitan Grinspun, Bernd Bickel, Yoshinori Dobashi
PublisherIEEE Computer Society
Pages33-38
Number of pages6
ISBN (Electronic)9783038680246
DOIs
Publication statusPublished - 1 Jan 2016
Externally publishedYes
Event24th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 2016 - Okinawa, Japan
Duration: 11 Oct 201614 Oct 2016

Publication series

NameProceedings - Pacific Conference on Computer Graphics and Applications
Volume2016-October
ISSN (Print)1550-4085

Conference

Conference24th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 2016
Country/TerritoryJapan
CityOkinawa
Period11/10/1614/10/16

Fingerprint

Dive into the research topics of 'Interactive multicut video segmentation'. Together they form a unique fingerprint.

Cite this