AI RESEARCH

From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation

arXiv CS.CV

ArXi:2605.25570v2 Announce Type: replace Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique opportunity to model motion with fine temporal precision.