Seeing Motion at Nighttime with an Event Camera

TL;DR

This paper introduces a novel event camera-based method for nighttime dynamic scene imaging, leveraging high temporal resolution and dynamic range to overcome limitations of traditional low-light imaging techniques.

Contribution

It proposes NER-Net, a new neural network with modules for event timestamp calibration and illumination awareness, and provides a large paired dataset for nighttime event imaging.

Findings

NER-Net outperforms existing methods in visual quality

The method demonstrates strong generalization on real-world datasets

The dataset RLED includes over 64,000 aligned images and events

Abstract

We focus on a very challenging task: imaging at nighttime dynamic scenes. Most previous methods rely on the low-light enhancement of a conventional RGB camera. However, they would inevitably face a dilemma between the long exposure time of nighttime and the motion blur of dynamic scenes. Event cameras react to dynamic changes with higher temporal resolution (microsecond) and higher dynamic range (120dB), offering an alternative solution. In this work, we present a novel nighttime dynamic imaging method with an event camera. Specifically, we discover that the event at nighttime exhibits temporal trailing characteristics and spatial non-stationary distribution. Consequently, we propose a nighttime event reconstruction network (NER-Net) which mainly includes a learnable event timestamps calibration module (LETC) to align the temporal trailing events and a non-uniform illumination aware module (NIAM) to stabilize the spatiotemporal distribution of events. Moreover, we construct a paired real low-light event dataset (RLED) through a co-axial imaging system, including 64,200 spatially and temporally aligned image GTs and low-light events. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art methods in terms of visual quality and generalization ability on real-world nighttime datasets. The project are available at: https://github.com/Liu-haoyue/NER-Net.