Yilun Wu, Federico Paredes-Vallés, Guido C. H. E. de Croon

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, at the same time 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 explicit correlation volumes as such search directions. We introduce IDNet (Iterative Deblurring Network), a lightweight yet high-performing event-based optical flow network directly estimating flow from event traces without using correlation volumes. We further propose two iterative update schemes: "ID" which iterates over the same batch of events, and "TID" which iterates over time with streaming events in an online fashion. Benchmark results show the "ID" scheme outperforms previous state-of-the-art by 9% of EPE with 52% fewer parameters and 77% savings in memory footprint, while the "TID" scheme is even more efficient promising 80% of compute savings and 18 times less latency at the cost of only 6% of performance drop.