I'm a computer vision researcher with an MASc in Computer Engineering from Queen's University. My work is on 6D object pose estimation: figuring out not just what an object is, but where it is and how it's oriented in 3D space.
I build full pipelines for this. Training segmentation and regression models, classical geometry methods like RANSAC, ICP, and Horn's method, and deploying the resulting inference pipelines in real-time robotic setups.
B2TFPose (my MASc thesis work, BMVC 2026, to appear): zero-shot 6DoF pose estimation of objects never seen in training, from a single RGB image and a CAD model. It uses one frozen DINOv3 backbone and no task-specific training.
