ROAM: A Rich Object Appearance Model with Application to Rotoscoping

Abstract

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. AbstractRotoscoping, 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 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.

Fast Online Object Tracking and Segmentation: A Unifying Approach

“…However, in this case the object representation consists of a binary segmentation mask which expresses whether or not a pixel belongs to the target [40]. Such a detailed representation is more desirable for applications that require pixel-level information, like video editing [38] and rotoscoping [37]. Understandably, producing pixel-level estimates requires more computational re-sources than a simple bounding box.…”

Akuisisi Foreground dan Background Berbasis Fitur DTC pada Matting Citra secara Otomatis

“…Rotoscoping menggunakan teknik Roto++ (Li et al, 2016) merupakan proses soft segmentation obyek foreground dan background dalam video. Untuk mempermudah proses tersebut, dikembangkan teknik ROAM (Miksik et al, 2017) yang merupakan pengembangan Grab-Cut (Rother, Kolmogorov and Blake, 2004). Segmentasi menggunakan constraned berdasarkan lokasi, skala serta model dari target digunakan (Long, Liu and Han, 2017) untuk memisahkan obyek dari video.…”