Seeing Motion at Nighttime with an Event Camera
Authors:
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 25648-25658
Abstract
We focus on a very challenging task: imaging at night-time 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.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62371203)
This publication has 67 references indexed in Scilit:
- DVS-Voltmeter: Stochastic Process-Based Event Simulator for Dynamic Vision Sensors2022
- Beyond Brightening Low-light ImagesInternational Journal of Computer Vision, 2021
- Learning to See in the Dark with Events2020
- Low Light Video Enhancement Using Synthetic Data Produced with an Intermediate Domain Mapping2020
- Reducing the Sim-to-Real Gap for Event Cameras2020
- Hybrid enhancement of infrared night vision imaging systemMultimedia Tools and Applications, 2019
- Learning Blind Video Temporal Consistency2018
- Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold RegularisationInternational Journal of Computer Vision, 2018
- LLNet: A deep autoencoder approach to natural low-light image enhancementPattern Recognition, 2017
- Visual adaptation in relation to brief conditioning stimuliProceedings of the Royal Society of London. B. Biological Sciences, 1947