Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis

计算机科学 降噪 加性高斯白噪声 人工智能 高斯噪声 块(置换群论) 噪音(视频) 卷积神经网络 网络体系结构 计算机视觉 白噪声 模式识别(心理学) 图像(数学) 数学 电信 计算机安全 几何学
作者
Kai Zhang,Yawei Li,Jingyun Liang,Jiezhang Cao,Yulun Zhang,Hao Tang,Deng-Ping Fan,Radu Timofte,Luc Van Gool
标识
DOI:10.1007/s11633-023-1466-0
摘要

While recent years have witnessed a dramatic upsurge of exploiting deep neural networks toward solving image denoising, existing methods mostly rely on simple noise assumptions, such as additive white Gaussian noise (AWGN), JPEG compression noise and camera sensor noise, and a general-purpose blind denoising method for real images remains unsolved. In this paper, we attempt to solve this problem from the perspective of network architecture design and training data synthesis. Specifically, for the network architecture design, we propose a swin-conv block to incorporate the local modeling ability of residual convolutional layer and non-local modeling ability of swin transformer block, and then plug it as the main building block into the widely-used image-to-image translation UNet architecture. For the training data synthesis, we design a practical noise degradation model which takes into consideration different kinds of noise (including Gaussian, Poisson, speckle, JPEG compression, and processed camera sensor noises) and resizing, and also involves a random shuffle strategy and a double degradation strategy. Extensive experiments on AGWN removal and real image denoising demonstrate that the new network architecture design achieves state-of-the-art performance and the new degradation model can help to significantly improve the practicability. We believe our work can provide useful insights into current denoising research.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
4秒前
6秒前
7秒前
joy发布了新的文献求助10
8秒前
CipherSage应助精明的天抒采纳,获得10
8秒前
Matthew_G完成签到,获得积分10
8秒前
lvsehx完成签到,获得积分10
9秒前
lvsehx发布了新的文献求助10
11秒前
微微完成签到 ,获得积分10
12秒前
13秒前
nansu完成签到,获得积分10
13秒前
虾米应助恶恶么v采纳,获得10
14秒前
16秒前
AM发布了新的文献求助10
16秒前
19秒前
lull发布了新的文献求助10
19秒前
21秒前
23秒前
23秒前
26秒前
十三发布了新的文献求助10
28秒前
Yangaaa发布了新的文献求助10
28秒前
无辜芷荷完成签到,获得积分10
29秒前
Patrick0614发布了新的文献求助10
30秒前
30秒前
30秒前
hjy发布了新的文献求助10
31秒前
mmill发布了新的文献求助10
31秒前
32秒前
乐乐乐乐乐乐应助AM采纳,获得10
33秒前
小星星应助Patrick0614采纳,获得10
35秒前
闲来饮茶完成签到,获得积分10
37秒前
YuchaoJia发布了新的文献求助10
37秒前
spark317发布了新的文献求助10
38秒前
38秒前
闲来饮茶发布了新的文献求助10
40秒前
youmuyou发布了新的文献求助50
43秒前
44秒前
NexusExplorer应助minagao采纳,获得10
45秒前
46秒前
高分求助中
Comprehensive natural products III : chemistry and biology 3000
进口的时尚——14世纪东方丝绸与意大利艺术 Imported Fashion:Oriental Silks and Italian Arts in the 14th Century 800
Glucuronolactone Market Outlook Report: Industry Size, Competition, Trends and Growth Opportunities by Region, YoY Forecasts from 2024 to 2031 800
Zeitschrift für Orient-Archäologie 500
The Collected Works of Jeremy Bentham: Rights, Representation, and Reform: Nonsense upon Stilts and Other Writings on the French Revolution 320
Equality: What It Means and Why It Matters 300
A new Species and a key to Indian species of Heirodula Burmeister (Mantodea: Mantidae) 300
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 物理化学 催化作用 细胞生物学 免疫学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3346534
求助须知:如何正确求助?哪些是违规求助? 2973237
关于积分的说明 8658336
捐赠科研通 2653621
什么是DOI,文献DOI怎么找? 1453288
科研通“疑难数据库(出版商)”最低求助积分说明 672801
邀请新用户注册赠送积分活动 662717