3D Human Motion Generation Using Learnt Motion Representations

In this internship, we aim to develop a machine-learning model that learns human pose and movements. Such
models can be used for AI-assisted human animation creation, motion refinement and denoising, video or imageto-
pose conversion, and motion editing. We plan to implement and push state-of-the-art human motion models by
taking inspiration from the advances in computer vision research. Consequently, the research results will be
published in peer-reviewed journals or computer vision venues, and the source code will be publicly available.
Another expected outcome of this internship is a toolbox for the animators at Ubisoft for game development.
Finally, we plan to collect information about the users’ interactions with this toolbox to be used on future research
on AI-assisted animation creation and editing.

Faculty Supervisor:

Ali Etemad

Student:

Partner:

Ubisoft Toronto

Discipline:

Computer science

Sector:

Information and cultural industries

University:

Queen's University

Program: