Abstract

We propose a design framework to assist with user-generated content in facial animation — without requiring any animation experience or ground truth reference. Where conventional prototyping methods rely on handcrafting by experienced animators, our approach looks to encode the role of the animator as an Evolutionary Algorithm acting on animation controls, driven by visual feedback from a user. Presented as a simple interface, users sample control combinations and select favourable results to influence later sampling. Over multiple iterations of disregarding unfavourable control values, parameters converge towards the user's ideal. We demonstrate our framework through two non-trivial applications: creating highly nuanced expressions by evolving control values of a face rig and non-linear motion through evolving control point positions of animation curves.

LanguageEnglish
Number of pages12
JournalComputer Graphics Forum
DOIs
StatusE-pub ahead of print - 1 Jan 2019

Keywords

  • animation interfaces
  • Animation → Animation Systems; Facial Animation; • Methods and Applications → Genetic Algorithms
  • facial animation
  • genetic algorithms
  • user-generated content

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Cite this

User-Guided Facial Animation through an Evolutionary Interface. / Reed, K.; Cosker, D.

In: Computer Graphics Forum, 01.01.2019.

Research output: Contribution to journalArticle

@article{5eb24166653a4ba1aa3f4f5bda94fd8b,
title = "User-Guided Facial Animation through an Evolutionary Interface",
abstract = "We propose a design framework to assist with user-generated content in facial animation — without requiring any animation experience or ground truth reference. Where conventional prototyping methods rely on handcrafting by experienced animators, our approach looks to encode the role of the animator as an Evolutionary Algorithm acting on animation controls, driven by visual feedback from a user. Presented as a simple interface, users sample control combinations and select favourable results to influence later sampling. Over multiple iterations of disregarding unfavourable control values, parameters converge towards the user's ideal. We demonstrate our framework through two non-trivial applications: creating highly nuanced expressions by evolving control values of a face rig and non-linear motion through evolving control point positions of animation curves.",
keywords = "animation interfaces, Animation → Animation Systems; Facial Animation; • Methods and Applications → Genetic Algorithms, facial animation, genetic algorithms, user-generated content",
author = "K. Reed and D. Cosker",
year = "2019",
month = "1",
day = "1",
doi = "10.1111/cgf.13612",
language = "English",
journal = "Computer Graphics Forum",
issn = "0167-7055",
publisher = "Wiley-Blackwell",

}

TY - JOUR

T1 - User-Guided Facial Animation through an Evolutionary Interface

AU - Reed, K.

AU - Cosker, D.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We propose a design framework to assist with user-generated content in facial animation — without requiring any animation experience or ground truth reference. Where conventional prototyping methods rely on handcrafting by experienced animators, our approach looks to encode the role of the animator as an Evolutionary Algorithm acting on animation controls, driven by visual feedback from a user. Presented as a simple interface, users sample control combinations and select favourable results to influence later sampling. Over multiple iterations of disregarding unfavourable control values, parameters converge towards the user's ideal. We demonstrate our framework through two non-trivial applications: creating highly nuanced expressions by evolving control values of a face rig and non-linear motion through evolving control point positions of animation curves.

AB - We propose a design framework to assist with user-generated content in facial animation — without requiring any animation experience or ground truth reference. Where conventional prototyping methods rely on handcrafting by experienced animators, our approach looks to encode the role of the animator as an Evolutionary Algorithm acting on animation controls, driven by visual feedback from a user. Presented as a simple interface, users sample control combinations and select favourable results to influence later sampling. Over multiple iterations of disregarding unfavourable control values, parameters converge towards the user's ideal. We demonstrate our framework through two non-trivial applications: creating highly nuanced expressions by evolving control values of a face rig and non-linear motion through evolving control point positions of animation curves.

KW - animation interfaces

KW - Animation → Animation Systems; Facial Animation; • Methods and Applications → Genetic Algorithms

KW - facial animation

KW - genetic algorithms

KW - user-generated content

UR - http://www.scopus.com/inward/record.url?scp=85063130435&partnerID=8YFLogxK

U2 - 10.1111/cgf.13612

DO - 10.1111/cgf.13612

M3 - Article

JO - Computer Graphics Forum

T2 - Computer Graphics Forum

JF - Computer Graphics Forum

SN - 0167-7055

ER -