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.
https://hal.archives-ouvertes.fr/hal-01378800
Contributeur : Nicolas Bonneel
<>
Soumis le : lundi 10 octobre 2016 - 17:53:03
Dernière modification le : jeudi 1 novembre 2018 - 01:19:48
Document(s) archivé(s) le : samedi 4 février 2017 - 01:28:04
Evgeny Levinkov, James Tompkin, Nicolas Bonneel, Steffen Kirchhoff, Bjoern Andres, et al.. Interactive Multicut Video Segmentation. Pacific Graphics, Oct 2016, Okinawa, Japan. 〈hal-01378800〉
