School of Computer Science and Statistics
Rachel McDonnell 
Recent generative animation models can create realistic character motion rather than simply replaying existing animation clips. In this project, you will use Epic Games’ new AnimGen framework and motion-capture data from the large-scale HiPHI dataset to investigate human-object interaction. The student will select a manageable subset of interactions, such as approaching, reaching for, picking up … Read more
In Virtual Reality, users typically expect their avatar to both look and move like them. But what happens when your virtual body responds to your actions while moving with the motion style of somebody else, or when your appearance is replaced by a highly realistic digital double of another person? In this project, the student … Read more
How we move through a crowd is influenced not only by where other people are, but also by how we perceive them. This project will investigate whether the appearance and proximity of virtual people influence how users behave when navigating through a crowd in Virtual Reality. The student will develop a VR crowd environment in … Read more
Recent advances in generative AI make it possible to realistically transform both a person’s face and voice while preserving their underlying behaviour. This project will develop an interactive AI virtual mirror in which participants see their face transformed into another photorealistic identity while their own facial expressions and head movements drive the generated face. The … Read more
This project will develop a procedural facial feature adjustment system for Unreal Engine MetaHumans that dynamically modifies key facial characteristics based on psychological associations between facial traits and personality impressions—for example, enlarging eyes to convey honesty or adjusting jawline to suggest dominance. The system will map established psychological findings about how facial features … Read more
This project aims to enhance the visual diversity and realism of crowds in real-time virtual environments by combining AI-driven texture generation for clothing with procedural variation techniques applied to a limited set of template MetaHumans in Unreal Engine. By leveraging state-of-the-art AI models to generate diverse, high-quality clothing textures dynamically, the project will create varied … Read more
This project will explore how users select and customize avatars within educational virtual environments and how these choices affect engagement and identification with the learning experience. The student will review existing avatar customization systems, focusing on how well they support user identity expression and ease of use in educational contexts. Using a prototype avatar customization … Read more
This project will investigate how two core gaze behaviors, mutual gaze and gaze cueing, influence user behavior and attention in dynamic virtual environments. In real-world interactions, direct eye contact increases social presence and engagement, while observing another person’s gaze direction can automatically shift our own attention. Using immersive virtual reality, this study will simulate a … Read more
[FYP] In this project, you will improve the realism of emotion on Metahumans in Unreal Engine by developing a realistic tear system, where tears are affected by gravity, and smudge in contact with make-up for added realism. Also part of the project will be motion capturing crying animations, and evaluating the resulting emotion with and … Read more
[MSc Level] We will collaborate with award-winning animation studio Cartoon Saloon to investigate perception of pose for stylized cartoon characters, such as those used in their films. Cartoon characters are often drawn to defy the laws of physics, and there is little known about perception of these characters – what makes a cartoon pose similar … Read more