MaSG2IM

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

Meta-learning for Image Generation/Manipulation using Scene Graphs

Thesis by: Sabrina Musatian
Advisor: Azade Farshad, Helisa Dhamo
Supervision by: Prof. Dr. Nassir Navab
Due date:

Abstract

Image generation using scene graphs in natural scenes is a challenging task in high image resolutions. In this project, we aim to improve the quality of image generation and manipulation from scene graphs using meta-learning approaches used for the few-shot learning problem. We plan to incorporate domain adaptation and information from synthetic images to learn a well-generalized model that adapts fast to new scenes.

Resources

Literature


Students.ProjectForm
Title: Meta-learning for Image Generation/Manipulation using Scene Graphs
Abstract: Image generation using scene graphs in natural scenes is a challenging task in high image resolutions. In this project, we aim to improve the quality of image generation and manipulation from scene graphs using meta-learning approaches used for the few-shot learning problem. We plan to incorporate domain adaptation and information from synthetic images to learn a well-generalized model that adapts fast to new scenes.
Student: Sabrina Musatian
Director: Prof. Dr. Nassir Navab
Supervisor: Azade Farshad, Helisa Dhamo
Type: Master Thesis
Area: Machine Learning, Computer Vision
Status: finished
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.3 - 11 Jul 2021 - 10:35 - AzadeFarshad