Lightweight Event-based Optical Flow Estimation via Iterative Deblurring

arXiv:2211.13726v4 Announce Type: replace
Abstract: Inspired by frame-based methods, state-of-the-art event-based optical flow networks rely on the explicit construction of correlation volumes, which are expensive to compute and store, rendering them unsuitable for robotic applications with limited compute and energy budget. Moreover, correlation volumes scale poorly with resolution, prohibiting them from estimating high-resolution flow. We observe that the spatiotemporally continuous traces of events provide a natural search direction for seeking pixel correspondences, obviating the need to rely on gradients of …

abstract applications art arxiv budget compute construction correlation cs.cv energy event flow iterative networks optical optical flow rendering resolution robotic scale state store them type via