AbstractImage editing is traditionally a labour intensive process involving professional software and human expertise.
Such a process is expensive and time consuming.
As a result, many individuals are not able to seamlessly express their creativity.
Therefore, there is a need for new image editing tools allowing for intuitive and advanced image edits.
In this thesis we propose novel algorithms that simplify the image editing pipeline and reduce the amount of labour involved.
We leverage new advances in artificial intelligence to bridge the gap between human-based edits and data-driven image edits.
We build upon existing models learned from data and propose four new solutions that allow users to edit images without prior knowledge on image editing.
We put particular emphasis on two application scenarios,
1) editing existing objects appearing in images (object-centric image editing),
2) synthesizing novel objects in images (object-centric image synthesis).
|Date of Award||21 Jul 2021|
|Supervisor||Darren Cosker (Supervisor) & Wenbin Li (Supervisor)|
- Image editing
- Computer vision
- Machine Learning