ROAM: A Rich Object Appearance Model with Application to Rotoscoping

Ondrej Miksik, Juan-Manuel Perez-Rua, Philip H. S. Torr, Patrick Perez
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Figure 1 : ROAM for video object segmentation. Designed to help rotoscoping, the proposed object appearance model allows the automatic delineation of a complex object in a shot, starting from an initial outline provided by the user. Abstract Rotoscoping, the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines. While pixel-wise segmentation techniques can help for this task, professional rotoscoping
more » ... tools rely on parametric curves that offer the artists a much better interactive control on the definition, editing and manipulation of the segments of interest. Sticking to this prevalent rotoscoping paradigm, we propose a novel framework to capture and track the visual aspect of an arbitrary object in a scene, given a first closed outline of this object. This model combines a collection of local foreground/background appearance models spread along the outline, a global appearance model of the enclosed object and a set of distinctive foreground landmarks. The structure of this rich appearance model allows simple initialization, efficient iterative optimization with exact minimization at each step, and on-line adaptation in videos. We demonstrate qualitatively and quantitatively the merit of this framework through comparisons with tools based on either dynamic segmentation with a closed curve or pixel-wise binary labelling. * Assert joint first authorship. J-M is also with Inria (Centre Rennes -Bretagne Atlantique, France).
doi:10.1109/cvpr.2017.785 dblp:conf/cvpr/MiksikPTP17 fatcat:5cmyhsw6v5fltjarwrcnpk55tm