👋

Hi!

I’m a computer vision researcher and engineer based in Tokyo, originally from Sydney, Australia. I work on 3D vision, generative models, neural rendering, and efficient machine learning systems.

I’m particularly interested in taking research all the way from an initial idea to something that actually works in practice — from problem formulation and model design through implementation, experimentation, and production deployment.

Much of my recent work has focused on photorealistic 3D humans, including avatar reconstruction, neural rendering, and real-time tracking. More broadly, I’m interested in representation learning, self-supervised learning, world models, and building efficient systems for visual intelligence.

Feel free to reach out on LinkedIn or GitHub if there’s anything you’d like to discuss!

Research interests: 3D vision · Neural rendering · Generative models · Self-supervised learning · World models · Representation learning · Efficient inference