Interactive Multicut Video Segmentation - Archive ouverte HAL Access content directly
Conference Papers Year :

Interactive Multicut Video Segmentation


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.
Fichier principal
Vignette du fichier
InteractiveMultilabelVideoSegmentation.pdf (5.81 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01378800 , version 1 (10-10-2016)


  • HAL Id : hal-01378800 , version 1


Evgeny E Levinkov, James Tompkin, Nicolas Bonneel, Steffen Kirchhoff, Bjoern E Andres, et al.. Interactive Multicut Video Segmentation. Pacific Graphics, Oct 2016, Okinawa, Japan. pp.33-38. ⟨hal-01378800⟩
422 View
196 Download


Gmail Facebook Twitter LinkedIn More