Dual-Exposure Imaging with Events

TL;DR

This paper introduces E-DEI, a novel event-based dual-exposure imaging algorithm that enhances low-light images by integrating high-temporal-resolution event data with dual-exposure images, addressing artifacts from motion and feature discrepancies.

Contribution

The paper proposes a dual-path network with a feature alignment and fusion module, and introduces a new dataset with paired images and events for low-light imaging tasks.

Findings

E-DEI outperforms existing methods on multiple datasets.

The proposed DFAF module effectively aligns and fuses features from dual exposures and events.

The dataset PIED provides a new benchmark for event-based low-light imaging.

Abstract

By combining complementary benefits of short- and long-exposure images, Dual-Exposure Imaging (DEI) enhances image quality in low-light scenarios. However, existing DEI approaches inevitably suffer from producing artifacts due to spatial displacement from scene motion and image feature discrepancies from different exposure times. To tackle this problem, we propose a novel Event-based DEI (E-DEI) algorithm, which reconstructs high-quality images from dual-exposure image pairs and events, leveraging high temporal resolution of event cameras to provide accurate inter-/intra-frame dynamic information. Specifically, we decompose this complex task into an integration of two sub-tasks, i.e., event-based motion deblurring and low-light image enhancement tasks, which guides us to design E-DEI network as a dual-path parallel feature propagation architecture. We propose a Dual-path Feature Alignment and Fusion (DFAF) module to effectively align and fuse features extracted from dual-exposure images with assistance of events. Furthermore, we build a real-world Dataset containing Paired low-/normal-light Images and Events (PIED). Experiments on multiple datasets show the superiority of our method. The code and dataset are available at github.