Qifeng Yu

Absolute pose estimation from event streams can now be achieved with unprecedented accuracy and efficiency, revolutionizing applications in robotics and augmented reality.

Event cameras can reconstruct the high-speed trajectories of warhead fragments with unprecedented accuracy, even amidst the chaos of detonation.

Asynchronous event cameras can achieve superior motion estimation accuracy, outperforming traditional methods by leveraging a novel minimal solver for full DoF egomotion.

Estimating joint torques non-invasively using image data could revolutionize biomechanics research and applications in uncontrolled environments.

Event cameras can now accurately measure high-speed 3D deformations of structures under extreme lighting, opening up new possibilities for monitoring the safety of critical infrastructure.

Achieve state-of-the-art atmospheric turbulence mitigation by modeling non-isoplanatic blur with Gaussian splatting, outperforming existing methods on both synthetic and real-world datasets.