Low-Light Video Enhancement with Synthetic Event Guidance

TL;DR

This paper introduces a novel low-light video enhancement method guided by synthetic events, which improves restoration quality and reduces artifacts in challenging low-light and fast-motion scenarios.

Contribution

It proposes a new framework using synthetic event guidance with two novel modules, outperforming existing methods in low-light video enhancement.

Findings

Outperforms existing LLVE methods on synthetic datasets

Effective in handling extreme low light and fast motion

Reduces multi-frame fusion artifacts

Abstract

Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving. Unlike single image low-light enhancement, most LLVE methods utilize temporal information from adjacent frames to restore the color and remove the noise of the target frame. However, these algorithms, based on the framework of multi-frame alignment and enhancement, may produce multi-frame fusion artifacts when encountering extreme low light or fast motion. In this paper, inspired by the low latency and high dynamic range of events, we use synthetic events from multiple frames to guide the enhancement and restoration of low-light videos. Our method contains three stages: 1) event synthesis and enhancement, 2) event and image fusion, and 3) low-light enhancement. In this framework, we design two novel modules (event-image fusion transform and event-guided dual branch) for the second and third stages, respectively. Extensive experiments show that our method outperforms existing low-light video or single image enhancement approaches on both synthetic and real LLVE datasets.