Roto++: accelerating professional rotoscoping using shape manifolds

Wenbin Li, Fabio Viola, Jonathan Starck, Gabriel J. Brostow, Neill Campbell

Research output: Contribution to journalArticle

  • 8 Citations

Abstract

Rotoscoping (cutting out different characters/objects/layers in raw video footage) is a ubiquitous task in modern post-production and represents a significant investment in person-hours. In this work, we study the particular task of professional rotoscoping for high-end, live action movies and propose a new framework that works with roto-artists to accelerate the workflow and improve their productivity. Working with the existing keyframing paradigm, our first contribution is the development of a shape model that is updated as artists add successive keyframes. This model is used to improve the output of traditional interpolation and tracking techniques, reducing the number of keyframes that need to be specified by the artist. Our second contribution is to use the same shape model to provide a new interactive tool that allows an artist to reduce the time spent editing each keyframe. The more keyframes that are edited, the better the interactive tool becomes, accelerating the process and making the artist more efficient without compromising their control. Finally, we also provide a new, professionally rotoscoped dataset that enables truly representative, real-world evaluation of rotoscoping methods. We used this dataset to perform a number of experiments, including an expert study with professional roto-artists, to show, quantitatively, the advantages of our approach.
LanguageEnglish
Article number62
JournalACM Transactions on Graphics
Volume35
Issue number4
DOIs
StatusPublished - 11 Jul 2016

Fingerprint

Interpolation
Productivity
Experiments

Cite this

Roto++: accelerating professional rotoscoping using shape manifolds. / Li, Wenbin; Viola, Fabio; Starck, Jonathan; Brostow, Gabriel J.; Campbell, Neill.

In: ACM Transactions on Graphics, Vol. 35, No. 4, 62, 11.07.2016.

Research output: Contribution to journalArticle

Li, Wenbin ; Viola, Fabio ; Starck, Jonathan ; Brostow, Gabriel J. ; Campbell, Neill. / Roto++: accelerating professional rotoscoping using shape manifolds. In: ACM Transactions on Graphics. 2016 ; Vol. 35, No. 4.
@article{1c8dc25fd3c948bbbe75f70c2e063dbe,
title = "Roto++: accelerating professional rotoscoping using shape manifolds",
abstract = "Rotoscoping (cutting out different characters/objects/layers in raw video footage) is a ubiquitous task in modern post-production and represents a significant investment in person-hours. In this work, we study the particular task of professional rotoscoping for high-end, live action movies and propose a new framework that works with roto-artists to accelerate the workflow and improve their productivity. Working with the existing keyframing paradigm, our first contribution is the development of a shape model that is updated as artists add successive keyframes. This model is used to improve the output of traditional interpolation and tracking techniques, reducing the number of keyframes that need to be specified by the artist. Our second contribution is to use the same shape model to provide a new interactive tool that allows an artist to reduce the time spent editing each keyframe. The more keyframes that are edited, the better the interactive tool becomes, accelerating the process and making the artist more efficient without compromising their control. Finally, we also provide a new, professionally rotoscoped dataset that enables truly representative, real-world evaluation of rotoscoping methods. We used this dataset to perform a number of experiments, including an expert study with professional roto-artists, to show, quantitatively, the advantages of our approach.",
author = "Wenbin Li and Fabio Viola and Jonathan Starck and Brostow, {Gabriel J.} and Neill Campbell",
year = "2016",
month = "7",
day = "11",
doi = "10.1145/2897824.2925973",
language = "English",
volume = "35",
journal = "ACM Transactions on Graphics",
issn = "0730-0301",
publisher = "Association for Computing Machinery",
number = "4",

}

TY - JOUR

T1 - Roto++: accelerating professional rotoscoping using shape manifolds

AU - Li, Wenbin

AU - Viola, Fabio

AU - Starck, Jonathan

AU - Brostow, Gabriel J.

AU - Campbell, Neill

PY - 2016/7/11

Y1 - 2016/7/11

N2 - Rotoscoping (cutting out different characters/objects/layers in raw video footage) is a ubiquitous task in modern post-production and represents a significant investment in person-hours. In this work, we study the particular task of professional rotoscoping for high-end, live action movies and propose a new framework that works with roto-artists to accelerate the workflow and improve their productivity. Working with the existing keyframing paradigm, our first contribution is the development of a shape model that is updated as artists add successive keyframes. This model is used to improve the output of traditional interpolation and tracking techniques, reducing the number of keyframes that need to be specified by the artist. Our second contribution is to use the same shape model to provide a new interactive tool that allows an artist to reduce the time spent editing each keyframe. The more keyframes that are edited, the better the interactive tool becomes, accelerating the process and making the artist more efficient without compromising their control. Finally, we also provide a new, professionally rotoscoped dataset that enables truly representative, real-world evaluation of rotoscoping methods. We used this dataset to perform a number of experiments, including an expert study with professional roto-artists, to show, quantitatively, the advantages of our approach.

AB - Rotoscoping (cutting out different characters/objects/layers in raw video footage) is a ubiquitous task in modern post-production and represents a significant investment in person-hours. In this work, we study the particular task of professional rotoscoping for high-end, live action movies and propose a new framework that works with roto-artists to accelerate the workflow and improve their productivity. Working with the existing keyframing paradigm, our first contribution is the development of a shape model that is updated as artists add successive keyframes. This model is used to improve the output of traditional interpolation and tracking techniques, reducing the number of keyframes that need to be specified by the artist. Our second contribution is to use the same shape model to provide a new interactive tool that allows an artist to reduce the time spent editing each keyframe. The more keyframes that are edited, the better the interactive tool becomes, accelerating the process and making the artist more efficient without compromising their control. Finally, we also provide a new, professionally rotoscoped dataset that enables truly representative, real-world evaluation of rotoscoping methods. We used this dataset to perform a number of experiments, including an expert study with professional roto-artists, to show, quantitatively, the advantages of our approach.

UR - http://dx.doi.org/10.1145/2897824.2925973

U2 - 10.1145/2897824.2925973

DO - 10.1145/2897824.2925973

M3 - Article

VL - 35

JO - ACM Transactions on Graphics

T2 - ACM Transactions on Graphics

JF - ACM Transactions on Graphics

SN - 0730-0301

IS - 4

M1 - 62

ER -