EvLight++: Low-Light Video Enhancement With an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More

计算机科学 人工智能 分割 事件(粒子物理) 计算机视觉 特征(语言学) 单眼 特征提取 注释 模式识别(心理学) 语义学(计算机科学) 图像分割 空间分析 目标检测 深度学习 图像(数学) 图像分辨率 时态数据库
作者
Kanghao Chen,Guoqiang Liang,Yunfan Lu,Hangyu Li,Lin Wang
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:48 (2): 1608-1625 被引量:18
标识
DOI:10.1109/tpami.2025.3617801
摘要

Event cameras offer significant advantages for low-light video enhancement, primarily due to their high dynamic range. Current research, however, is severely limited by the absence of large-scale, real-world, and spatio-temporally aligned event-video datasets. To address this, we introduce a large-scale dataset with over 30,000 pairs of frames and events captured under varying illumination. This dataset was curated using a robotic arm that traces a consistent non-linear trajectory, achieving spatial alignment precision under 0.03 mm and temporal alignment with errors under 0.01 s for 90% of the dataset. Based on the dataset, we propose EvLight++, a novel event-guided low-light video enhancement approach designed for robust performance in real-world scenarios. First, we design a multi-scale holistic fusion branch to integrate structural and textural information from both images and events. To counteract variations in regional illumination and noise, we introduce Signal-to-Noise Ratio (SNR)-guided regional feature selection, enhancing features from high SNR regions and augmenting those from low SNR regions by extracting structural information from events. To incorporate temporal information and ensure temporal coherence, we further introduce a recurrent module and temporal loss in the whole pipeline. Extensive experiments on ours and the synthetic SDSD dataset demonstrate that EvLight++ significantly outperforms both single image- and video-based methods by 1.37 dB and 3.71 dB, respectively. To further explore its potential in downstream tasks like semantic segmentation and monocular depth estimation, we extend our datasets by adding pseudo segmentation and depth labels via meticulous annotation efforts with foundation models. Experiments under diverse low-light scenes show that the enhanced results achieve a 15.97% improvement in mIoU for semantic segmentation.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
传奇3的应助被小糖采纳,获得10
刚刚
枫叶完成签到,获得积分10
刚刚
1秒前
三三一发布了新的文献求助10
1秒前
Alvin_Bell发布了新的文献求助10
1秒前
鲸落小小的应助被耶汁采纳,获得10
2秒前
李乐乐完成签到,获得积分10
3秒前
3秒前
Fang完成签到 ,获得积分10
3秒前
dew的应助被xucc采纳,获得50
3秒前
Akim的应助被李琛采纳,获得10
4秒前
4秒前
情木花肆发布了新的文献求助10
4秒前
4秒前
5秒前
Brightfuture完成签到,获得积分10
5秒前
xiaxia发布了新的文献求助10
5秒前
爆米花的应助被自由棉花糖采纳,获得10
5秒前
Owen的应助被RAN采纳,获得10
6秒前
xy发布了新的文献求助10
6秒前
kamenashi完成签到,获得积分10
7秒前
ChemPu完成签到,获得积分10
7秒前
7秒前
xiaotian发布了新的文献求助10
7秒前
慕新完成签到,获得积分10
7秒前
谦让的晟睿完成签到 ,获得积分10
7秒前
Shirosagi完成签到,获得积分10
8秒前
8秒前
hydargyrum发布了新的文献求助30
8秒前
养猪匠完成签到,获得积分10
8秒前
zz完成签到 ,获得积分10
8秒前
zm发布了新的文献求助10
9秒前
9秒前
9秒前
9秒前
赵西里完成签到,获得积分10
9秒前
10秒前
怡然蘑菇完成签到,获得积分10
10秒前
传奇3的应助被炸鸡柳大王采纳,获得10
10秒前
lixixi完成签到,获得积分10
11秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180531
求助须知:如何正确求助?哪些是违规求助? 9570507
关于积分的说明 21812974
捐赠科研通 7776619
什么是DOI,文献DOI怎么找? 3433286
关于科研通互助平台的介绍 2557539
邀请新用户注册赠送积分活动 2479185