Receding-Horizon Maximum-Likelihood Estimation of Neural-ODE Dynamics and Thresholds from Event Cameras

TL;DR

This paper introduces a receding-horizon maximum-likelihood method for online identification of Neural ODE dynamics and thresholds from event camera data, enabling real-time parameter estimation.

Contribution

It develops a novel online estimation approach that jointly recovers Neural ODE parameters and contrast thresholds from event streams using a receding-horizon gradient-based method.

Findings

Successfully recovers dynamics parameters and contrast threshold in synthetic experiments.

Characterizes accuracy-latency trade-offs based on window length.

Demonstrates joint recovery capability from streaming event data.

Abstract

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.