The aim of this project is to develop a graphical

This preview shows page 24 - 26 out of 30 pages.

applications. The aim of this project is to develop a graphical user interface for existing film analysis software at the department and rewrite/optimize the current software from matlab to python. The software will be used by the post graduate, graduate students and clinical medical physicists to accurately analyze the dosimetry films. Description of company/Research lab Medical physics unit at the Jewish General hospital consists of post graduate, graduate and undegraduate students in medical physics, computer science, engineering, biology and physiology working together with faculty from department of oncology, biomedical engineering, physics and clinical medical physics to solve clinical problems and limitations in cancer care and treatment of cancer patients. Type of project:Design Projects (teams of 2 - 4 students), Honours Thesis (single student working alone) Exploration of style mixing on StyleGAN2 to design new paradigms of interaction for avatar-creator interfaces Project Advisor(s):Jeremy Cooperstock, CIM, McGill, [email protected]; , Project Description This project focuses on the graphical synthesis of avatars that can be customized by patients and therapists, for an Avatar Therapy project (). The interface for avatar creation must provide users with a great variety of customization options to closely match patients' mental representation of the hallucinations while keeping interactions as simple as possible. These constraints motivated the development of a machine learning approach based on Generative Adversarial Networks (GANs), which are state-of-the-art networks to generate high-quality and high-resolution faces. The main challenge of this approach is to design new interaction paradigms to enable a non-engineer user to control the output of the network and converge towards a face that makes patients feel they are in the presence of their hallucination. We generate faces using the open source StyleGAN2 network. This is trained using style mixing regularization, which is a regularization technique based on style transfer. It enables the network to specialize layers into synthesizing different levels of details in the output face. This particular training method can be leveraged to perform style mixing (), generating a new output that combines coarse aspects of one face with finer aspects of a second one,. Project objectives, in chronological order, are as follows:
ECSE 458N1/478N1 List of Projects offered for Fall 2020-Win 2021 Updated: 2020-09-08 9:42 PM1. gain familiarity with the framework, in particular, the style mixing scripts, and reproduce the results of Karras et al.'s StyleGAN2 paper () 2. generate different design ideas for a UI based on style mixing for avatar creation implement the most promising design preferably under the format of a web application 3. proceed with user testing to determine the validity of the style mixing approach, analyze the

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture