Knowledge Externalization from Image-to-Image Translation

Abstract

We present a novel Animation CelebHeads dataset (AnimeCeleb) to address an animation head reenactment. Different from previous animation head datasets, we utilize a 3D animation models as the controllable image samplers, which can provide a large amount of head images with their corresponding detailed pose annotations. To facilitate a data creation process, we build a semi-automatic pipeline leveraging an open 3D computer graphics software with a developed annotation system. After training with the AnimeCeleb, recent head reenactment models produce high-quality animation head reenactment results, which are not achievable with existing datasets. Furthermore, motivated by metaverse application, we propose a novel pose mapping method and architecture to tackle a cross-domain head reenactment task. During inference, a user can easily transfer ones motion to an arbitrary animation head. Experiments demonstrate a usefulness of the AnimeCeleb to train animation head reenactment models, and the superiority of our cross domain head reenactment model compared to state-of-the-art methods. Our dataset and code are available at https://github.com/kangyeolk/AnimeCeleb. This work has been published in ECCV22.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 02, 2023
Accession Number
AD1205076

Entities

People

  • Jaegul Choo

Organizations

  • KAIST

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Buildings And Structures
  • Computer Graphics
  • Computer Vision
  • Computers
  • Cross Domain
  • Graphics
  • Image Processing
  • Image Recognition
  • Information Processing
  • Information Systems
  • Neural Networks
  • Pattern Recognition
  • Recognition
  • Semantics
  • Translations
  • Websites

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Neural Network Machine Learning.
  • Phased Array Antenna Design.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks