Computer Vision

A 25-μs/inf Event-driven Graph Neural Network Processor with Spatiotemporal Caching and Spline Convolution for Ultra-low-latency AI at the Edge

Neural Events: Discrete Asynchronous Autoencoders for Event-Based Vision

ETAP: Event-based Tracking of Any Point

EqNIO: Subequivariant Neural Inertial Odometry

A Linear N-Point Solver for Structure and Motion from Asynchronous Tracks

An N-Point Linear Solver for Line and Motion Estimation with Event Cameras

Note This paper lead to an oral at CVPR 2024 in Seattle!

A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception

Note The work by Asude Aydin that contributed to the paper “A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception” at a CVPR Workshop 2024 lead to a UZH …

Low Latency Automotive Vision with Event Cameras

Note This work lead to me winning the UZH Annual Award, which is awarded to the best Ph.D. in the department of Informatics!

E-Calib: A fast, robust, and accurate calibration toolbox for event cameras

Deep Visual Odometry with Events and Frames