dc.contributor.advisor |
Fernando S |
|
dc.contributor.author |
Udawatta PN |
|
dc.date.accessioned |
2022 |
|
dc.date.available |
2022 |
|
dc.date.issued |
2022 |
|
dc.identifier.citation |
Udawatta, P. N. (2022). 2D Human animation synthesis from videos using generative adversarial neural networks [Master's theses, University of Moratuwa]. Institutional Repository University of Moratuwa. http://dl.lib.uom.lk/handle/123/21479 |
|
dc.identifier.uri |
http://dl.lib.uom.lk/handle/123/21479 |
|
dc.description.abstract |
Synthesizing 2D human animation has many industrial applications yet is currently done manually
by animators utilizing time and resources. Therefore, many types of research have been conducted
to synthesize human animation using artificial intelligence techniques. However, these approaches
lack the quality as well as capability to generalize to various visual styles. Thus, synthesizing
high-quality human animations across different visual styles remains a research challenge
We hypothesize that given video references for motion and appearance, synthesizing high-quality
human animations across a variety of visual styles can be achieved via generative adversarial
networks.
Here we have come up with the solution known as HumAS-GAN, an acronym for Human
Animation Synthesis Generative Adversarial Networks. HumAS-GAN accepts video references
for motion and appearance and synthesis 2d Human animations. HumAS-GAN has three main
modules, motion extraction, motion synthesis, and appearance synthesis. In motion extraction, the
motion information is extracted via pre-trained human pose extraction [21], The motion synthesis
module syntheses a motion representation matching the target human’s body structure which is
then combined with the human pose coordinates to be used by the appearance synthesis module to
generate the Human animation. HumAS-GAN is focused on improving the quality of the
animation as well as the ability to use cross-domain/visual-style references to generate animation.
This solution will be beneficial for many multimedia-based industries as it is capable of generating
high human animations and quickly switching to any visual style they prefer.
HumAS-GAN is evaluated against other methods using a custom dataset and a set of 3 experiments
designed to evaluate the capability of generating human animations across various visual styles.
Evaluations results prove the superiority of HumAS-GAN over other methods in synthesizing
high-quality 2d human animations across a variety of visual styles. |
en_US |
dc.language.iso |
en |
en_US |
dc.subject |
HUMAN ANIMATION SYNTHESIS ALGORITHM |
en_US |
dc.subject |
2D HUMAN ANIMATIONS |
en_US |
dc.subject |
GENERATIVE ADVERSARIAL NEURAL NETWORKS |
en_US |
dc.subject |
2D HUMAN ANIMATION SYNTHESIS |
en_US |
dc.subject |
INFORMATION TECHNOLOGY -Dissertation |
en_US |
dc.subject |
COMPUTATIONAL MATHEMATICS -Dissertation |
en_US |
dc.subject |
ARTIFICIAL INTELLIGENCE -Dissertation |
en_US |
dc.title |
2D Human animation synthesis from videos using generative adversarial neural networks |
en_US |
dc.type |
Thesis-Abstract |
en_US |
dc.identifier.faculty |
IT |
en_US |
dc.identifier.degree |
MSc in Artificial Intelligence |
en_US |
dc.identifier.department |
Department of Computational Mathematics |
en_US |
dc.date.accept |
2022 |
|
dc.identifier.accno |
TH5013 |
en_US |