Event-Driven Video Restoration With Spiking-Convolutional Architecture

计算机科学 卷积神经网络 人工智能 去模糊 事件(粒子物理) 模式识别(心理学) 计算机视觉 图像复原 图像处理 图像(数学) 物理 量子力学
作者
Chengzhi Cao,Xueyang Fu,Yurui Zhu,Zhijing Sun,Zheng-Jun Zha
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:: 1-15 被引量:1
标识
DOI:10.1109/tnnls.2023.3329741
摘要

With high temporal resolution, high dynamic range, and low latency, event cameras have made great progress in numerous low-level vision tasks. To help restore low-quality (LQ) video sequences, most existing event-based methods usually employ convolutional neural networks (CNNs) to extract sparse event features without considering the spatial sparse distribution or the temporal relation in neighboring events. It brings about insufficient use of spatial and temporal information from events. To address this problem, we propose a new spiking-convolutional network (SC-Net) architecture to facilitate event-driven video restoration. Specifically, to properly extract the rich temporal information contained in the event data, we utilize a spiking neural network (SNN) to suit the sparse characteristics of events and capture temporal correlation in neighboring regions; to make full use of spatial consistency between events and frames, we adopt CNNs to transform sparse events as an extra brightness prior to being aware of detailed textures in video sequences. In this way, both the temporal correlation in neighboring events and the mutual spatial information between the two types of features are fully explored and exploited to accurately restore detailed textures and sharp edges. The effectiveness of the proposed network is validated in three representative video restoration tasks: deblurring, super-resolution, and deraining. Extensive experiments on synthetic and real-world benchmarks have illuminated that our method performs better than existing competing methods.
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
龍Ryu完成签到,获得积分10
刚刚
内向凌兰发布了新的文献求助10
1秒前
伍秋望完成签到,获得积分10
1秒前
2秒前
3秒前
跳跃发布了新的文献求助10
4秒前
持卿应助宗磬采纳,获得20
4秒前
4秒前
花生油炒花生米完成签到 ,获得积分10
4秒前
Riki完成签到,获得积分10
6秒前
虚幻白玉发布了新的文献求助10
6秒前
德行天下完成签到,获得积分10
6秒前
Jenny应助lan采纳,获得10
7秒前
fztnh完成签到,获得积分10
7秒前
上官若男应助lyz666采纳,获得10
7秒前
顾念完成签到 ,获得积分10
7秒前
277发布了新的文献求助10
8秒前
小二郎应助GCD采纳,获得10
9秒前
hhhhhh完成签到 ,获得积分10
9秒前
甜味拾荒者完成签到,获得积分10
11秒前
小二郎应助BONBON采纳,获得10
11秒前
12秒前
charllie完成签到 ,获得积分10
12秒前
空禅yew完成签到,获得积分10
13秒前
坚强亦丝应助跳跃采纳,获得10
15秒前
英俊的铭应助cc采纳,获得10
15秒前
huangsan完成签到,获得积分10
15秒前
匹诺曹完成签到,获得积分10
15秒前
16秒前
华仔应助进取拼搏采纳,获得10
16秒前
17秒前
dingdong发布了新的文献求助10
17秒前
you完成签到 ,获得积分10
18秒前
qwf完成签到 ,获得积分10
18秒前
19秒前
万能图书馆应助一一采纳,获得10
19秒前
执着跳跳糖完成签到 ,获得积分10
20秒前
阳yang完成签到,获得积分10
20秒前
牛头人完成签到,获得积分10
20秒前
21秒前
高分求助中
Continuum Thermodynamics and Material Modelling 3000
Production Logging: Theoretical and Interpretive Elements 2700
Social media impact on athlete mental health: #RealityCheck 1020
Ensartinib (Ensacove) for Non-Small Cell Lung Cancer 1000
Unseen Mendieta: The Unpublished Works of Ana Mendieta 1000
Bacterial collagenases and their clinical applications 800
El viaje de una vida: Memorias de María Lecea 800
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 有机化学 生物化学 物理 纳米技术 计算机科学 内科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 量子力学 光电子学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3527961
求助须知:如何正确求助?哪些是违规求助? 3108159
关于积分的说明 9287825
捐赠科研通 2805882
什么是DOI,文献DOI怎么找? 1540070
邀请新用户注册赠送积分活动 716926
科研通“疑难数据库(出版商)”最低求助积分说明 709808