Learning to Super Resolve Intensity Images from Events

Abstract

An event camera detects per-pixel intensity difference and produces asynchronous event stream with low latency, high dynamic sensing range, and low power consumption. As a trade-off, the event camera has low spatial resolution. We propose an end-to-end network to reconstruct high resolution, high dynamic range (HDR) images from the event streams. The reconstructed images using the proposed method is in better quality than the combination of state-ofthe-art intensity image reconstruction algorithms and the state-of-the-art super resolution schemes. We further evaluate our algorithm on multiple real-world sequences showing the ability to generate high quality images in the zeroshot cross dataset transfer setting.