Adaptive Dynamic Filtering Network for Image Denoising

计算机科学 卷积(计算机科学) 特征(语言学) 核(代数) 块(置换群论) 背景(考古学) 滤波器(信号处理) 人工智能 模式识别(心理学) 算法 计算机视觉 人工神经网络 数学 古生物学 语言学 哲学 几何学 组合数学 生物
作者
Hao Shen,Zhong‐Qiu Zhao,Wandi Zhang
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence [Association for the Advancement of Artificial Intelligence (AAAI)]
卷期号:37 (2): 2227-2235 被引量:20
标识
DOI:10.1609/aaai.v37i2.25317
摘要

In image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. This practice, however, also leads to the loss of high-frequency information and fails to consider within-scale characteristics. Recently, dynamic convolution has exhibited powerful capabilities in processing high-frequency information (e.g., edges, corners, textures), but previous works lack sufficient spatial contextual information in filter generation. To alleviate these issues, we propose to employ dynamic convolution to improve the learning of high-frequency and multi-scale features. Specifically, we design a spatially enhanced kernel generation (SEKG) module to improve dynamic convolution, enabling the learning of spatial context information with a very low computational complexity. Based on the SEKG module, we propose a dynamic convolution block (DCB) and a multi-scale dynamic convolution block (MDCB). The former enhances the high-frequency information via dynamic convolution and preserves low-frequency information via skip connections. The latter utilizes shared adaptive dynamic kernels and the idea of dilated convolution to achieve efficient multi-scale feature extraction. The proposed multi-dimension feature integration (MFI) mechanism further fuses the multi-scale features, providing precise and contextually enriched feature representations. Finally, we build an efficient denoising network with the proposed DCB and MDCB, named ADFNet. It achieves better performance with low computational complexity on real-world and synthetic Gaussian noisy datasets. The source code is available at https://github.com/it-hao/ADFNet.
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
yar应助朱哦哦采纳,获得10
刚刚
任昱琦完成签到 ,获得积分10
1秒前
深情安青应助顺利的寄琴采纳,获得10
1秒前
852应助水果咔咔咔采纳,获得10
2秒前
2秒前
昆明官渡酒店完成签到,获得积分20
2秒前
鹏虫虫发布了新的文献求助10
3秒前
3秒前
科研通AI2S应助Billy采纳,获得10
3秒前
3秒前
4秒前
CodeCraft应助甜甜的亦寒采纳,获得10
4秒前
怡然宛凝发布了新的文献求助10
5秒前
烟花应助魁梧的涵柏采纳,获得10
5秒前
5秒前
li完成签到,获得积分10
5秒前
晓晓完成签到,获得积分10
5秒前
酷波er应助石mx采纳,获得10
5秒前
旦皋完成签到,获得积分10
6秒前
lalala发布了新的文献求助10
6秒前
6秒前
qr完成签到,获得积分10
7秒前
笨笨以莲发布了新的文献求助10
7秒前
李健的小迷弟应助梓榆采纳,获得30
7秒前
科研通AI2S应助皇帝帅哥哥采纳,获得10
8秒前
斯文败类应助wwww采纳,获得10
9秒前
9秒前
周国超完成签到,获得积分10
9秒前
9秒前
稳重冰岚完成签到,获得积分10
9秒前
9秒前
朱哦哦完成签到,获得积分20
10秒前
clocksoar完成签到,获得积分10
10秒前
清脆的夜云完成签到,获得积分10
10秒前
qr发布了新的文献求助10
10秒前
ysy发布了新的文献求助10
11秒前
苏墨白完成签到,获得积分10
11秒前
黑夜的冰之歌完成签到,获得积分10
12秒前
Orange应助周国超采纳,获得10
12秒前
13秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 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 3970632
求助须知:如何正确求助?哪些是违规求助? 3515261
关于积分的说明 11177794
捐赠科研通 3250448
什么是DOI,文献DOI怎么找? 1795314
邀请新用户注册赠送积分活动 875781
科研通“疑难数据库(出版商)”最低求助积分说明 805073