Image all-in-one adverse weather removal via dynamic model weights generation

卷积(计算机科学) 卷积神经网络 特征(语言学) 代表(政治) 特征学习 模式识别(心理学) 人工智能 计算机科学 人工神经网络 数据挖掘 政治学 语言学 政治 哲学 法学
作者
Yecong Wan,Mingwen Shao,Yuanshuo Cheng,Wangmeng Zuo
出处
期刊:Knowledge Based Systems [Elsevier BV]
卷期号:302: 112324-112324
标识
DOI:10.1016/j.knosys.2024.112324
摘要

Restoring image under multiple weather conditions in an all-in-one fashion remains a formidable challenge due to images captured under different weather conditions exhibit different degradation characteristics and patterns. However, existing all-in-one adverse weather removal methods mainly focus on learning shared generic knowledge of multiple weather conditions via fixed network parameters, which fails to adjust for different instances to fit exclusive features characterization of specific weather conditions. To tackle this issue, we propose a novel dynamic weights generation network (DwGN) that can adaptively mine and extract instance-exclusive degradation features for different weather conditions via dynamically generated convolutional weights. Specifically, we first propose two fundamental dynamic weights convolutions, which can automatically generate optimal convolutional weights for distinct pending features via a lightweight yet efficient mapping layer. The predicted convolutional weights are then incorporated into the convolution operation to extract instance-exclusive features for different weather conditions. Building upon the dynamic weights convolutions, we further devise a tailored weight adaptive Transformer blocks (WATB) which consists of two core modules: half-dynamic multi-head cross-attention (HDMC) that performs exclusive-generic feature interaction, and half-dynamic feed-forward network (HDFN) that performs selected exclusive-generic feature transformation and aggregation. Considering communal features shared between different weather conditions (e.g., background representation), both HDMC and HDFN deploy only half of the dynamic weights convolutions for instance-exclusive feature characterization, while still deploying half of the static convolutions to characterize generic features. Through adaptive weight tuning, our DwGN can adaptively adapt to different weather scenarios and effectively capture the instance-exclusive degradation features, thus enjoying better flexibility and adaptability under all-in-one adverse weather removal. Extensive experiments demonstrate that our DwGN performs favorably against state-of-the-art algorithms. In particular, our proposed DwGN achieves the best PSNR and SSIM scores on all five tasks both in the task-specific setting and in the all-in-one setting. Furthermore, our method has shown consistent performance improvement in both real-world and high-level visual applications. The implementation code is available at https://github.com/Jeasco/DwGN.
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
冷静傲丝完成签到 ,获得积分10
1秒前
自然的雨发布了新的文献求助10
2秒前
3秒前
雪白的山雁完成签到 ,获得积分10
3秒前
耶耶耶完成签到 ,获得积分10
5秒前
liberation完成签到 ,获得积分0
6秒前
fiell发布了新的文献求助10
8秒前
8秒前
小大巫完成签到,获得积分10
8秒前
as完成签到,获得积分20
8秒前
xzy998应助默默的巧荷采纳,获得10
8秒前
9秒前
兴奋曼凡完成签到,获得积分10
9秒前
10秒前
drzz完成签到,获得积分10
12秒前
岂有此李完成签到,获得积分10
12秒前
坚强的依凝完成签到,获得积分10
13秒前
14秒前
昏昏完成签到 ,获得积分10
14秒前
不过尔尔完成签到 ,获得积分10
15秒前
刘宏完成签到,获得积分10
16秒前
可以完成签到,获得积分10
16秒前
17秒前
坚强枫完成签到,获得积分10
18秒前
默默的巧荷完成签到,获得积分10
19秒前
一叶知秋完成签到,获得积分10
20秒前
小杰瑞完成签到,获得积分20
20秒前
希望天下0贩的0应助可以采纳,获得10
20秒前
白色梨花发布了新的文献求助10
20秒前
21秒前
包容柜子发布了新的文献求助10
21秒前
fiell完成签到,获得积分10
22秒前
眼睛大的擎苍给眼睛大的擎苍的求助进行了留言
22秒前
呆萌滑板完成签到 ,获得积分10
23秒前
23秒前
瑶瑶完成签到,获得积分10
24秒前
小猪找库里完成签到,获得积分10
25秒前
zhuzhen007完成签到 ,获得积分10
26秒前
淡定的秀发完成签到,获得积分10
26秒前
xuan完成签到,获得积分10
28秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038446
求助须知:如何正确求助?哪些是违规求助? 3576149
关于积分的说明 11374627
捐赠科研通 3305875
什么是DOI,文献DOI怎么找? 1819354
邀请新用户注册赠送积分活动 892680
科研通“疑难数据库(出版商)”最低求助积分说明 815048