Receding-Horizon Maximum-Likelihood Estimation of Neural-ODE Dynamics and Thresholds from Event Cameras
This addresses online identification of dynamics for event-based vision systems, which is incremental as it builds on existing Neural ODE and point process methods.
The paper tackles online maximum-likelihood estimation of continuous-time dynamics from event camera streams, using a Neural ODE and a history-dependent point process model, and demonstrates joint recovery of dynamics parameters and contrast thresholds in synthetic experiments with accuracy-latency trade-offs.
Event cameras emit asynchronous brightness-change events where each pixel triggers an event when the last event exceeds a threshold, yielding a history-dependent measurement model. We address online maximum-likelihood identification of continuous-time dynamics from such streams. The latent state follows a Neural ODE and is mapped to predicted log-intensity through a differentiable state-to-image model. We model events with a history-dependent marked point process whose conditional intensity is a smooth surrogate of contrast-threshold triggering, treating the contrast threshold as an unknown parameter. The resulting log-likelihood consists of an event term and a compensator integral. We propose a receding-horizon estimator that performs a few gradient steps per update on a receding horizon window. For streaming evaluation, we store two scalars per pixel (last-event time and estimated log-intensity at that time) and approximate the compensator via Monte Carlo pixel subsampling. Synthetic experiments demonstrate joint recovery of dynamics parameters and the contrast threshold, and characterize accuracy--latency trade-offs with respect to the window length.