Reconstructing Production Data from Drawn Limited Animation

Information

• Publication Type: Master Thesis
• Workgroup(s)/Project(s):
  • Rendering and Modeling
• Date: September 2023
• Date (Start): February 2020
• Date (End): 9. March 2023
• Second Supervisor: Joao Afonso Cardoso
• Diploma Examination: 9. March 2023
• Open Access: yes
• First Supervisor: Michael Wimmer
• Pages: 86
• Keywords: Limited animation, Line arts, Semantic image segmentation

Abstract

The creation of traditional animation is performed in multiple steps, creating various intermediary products. Image processing and machine learning could be used for the automation of some of these time-consuming steps to help animators and studios. However, machine-learning solutions require large amounts of example data, which are not available for the intermediary products of animation. On the other hand, final animation is more easily available through public datasets, video releases, and streaming services. This work aims to bridge this gap by creating a tool to predict intermediary products of animation from frames of the final video, using machine learning. The predicted production data can then be used for further research. In particular, frames of traditional animation are made out of background and foreground elements, which are produced through different workflows. Foreground elements are created by first creating color-coded lineart. These are then colored and composited with the background. In this work, machine learning is used to undo these steps by separating a final frame into the foreground and background and recreating the lineart from the former.

Additional Files and Images

Weblinks

• Entry in reposiTUm (TU Wien Publication Database)
• DOI: 10.34726/hss.2023.82729

BibTeX

@mastersthesis{Kugler-2021,
  title =      "Reconstructing Production Data from Drawn Limited Animation",
  author =     "Felix Kugler",
  year =       "2023",
  abstract =   "The creation of traditional animation is performed in
               multiple steps, creating various intermediary products.
               Image processing and machine learning could be used for the
               automation of some of these time-consuming steps to help
               animators and studios. However, machine-learning solutions
               require large amounts of example data, which are not
               available for the intermediary products of animation. On the
               other hand, final animation is more easily available through
               public datasets, video releases, and streaming services.
               This work aims to bridge this gap by creating a tool to
               predict intermediary products of animation from frames of
               the final video, using machine learning. The predicted
               production data can then be used for further research. In
               particular, frames of traditional animation are made out of
               background and foreground elements, which are produced
               through different workflows. Foreground elements are created
               by first creating color-coded lineart. These are then
               colored and composited with the background. In this work,
               machine learning is used to undo these steps by separating a
               final frame into the foreground and background and
               recreating the lineart from the former.",
  month =      sep,
  pages =      "86",
  address =    "Favoritenstrasse 9-11/E193-02, A-1040 Vienna, Austria",
  school =     "Research Unit of Computer Graphics, Institute of Visual
               Computing and Human-Centered Technology, Faculty of
               Informatics, TU Wien",
  keywords =   "Limited animation, Line arts, Semantic image segmentation",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2023/Kugler-2021/",
}