Event-camera VOExpert
Real-time Event-camera Stereo Visual Odometry via Keytime Gaussian Process Regression
This preprint presents a real-time stereo visual odometry system for event cameras that represents the trajectory as a Gaussian process with sparse keytime states instead of one state per event observation. It achieves 22 Hz on MVSEC and 6 Hz on DSEC, with relative translation and rotation errors roughly an order of magnitude lower than the discrete ES-PTAM baseline. The approach preserves asynchronous event timing while making continuous-time estimation tractable for real-time operation.