Knowledge Commons of Institute of Automation,CAS
Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis | |
Kai Zhang1; Yawei Li1; Jingyun Liang1; Jiezhang Cao1; Yulun Zhang1; Hao Tang1; Deng-Ping Fan1; Radu Timofte2; Luc Van Gool1,3 | |
发表期刊 | Machine Intelligence Research
![]() |
ISSN | 2731-538X |
2023 | |
卷号 | 20期号:6页码:822-836 |
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. The source code is available at https://github.com/cszn/SCUNet. |
关键词 | Blind image denoising, real image denosing data synthesis, Transformer, image signal processing (ISP) pipeline |
DOI | 10.1007/s11633-023-1466-0 |
七大方向——子方向分类 | 其他 |
国重实验室规划方向分类 | 其他 |
是否有论文关联数据集需要存交 | 否 |
中文导读 | https://mp.weixin.qq.com/s/ZFn2nCFmIA7ePp3GlXD8rw |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56012 |
专题 | 学术期刊_Machine Intelligence Research |
作者单位 | 1.Computer Vision Lab, ETH Zürich, Zürich 8092, Switzerland 2.Computer Vision Lab, University of Würzburg, Würzburg 97074, Germany 3.KU Leuven, Leuven 3000, Belgium |
推荐引用方式 GB/T 7714 | Kai Zhang,Yawei Li,Jingyun Liang,et al. Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis[J]. Machine Intelligence Research,2023,20(6):822-836. |
APA | Kai Zhang.,Yawei Li.,Jingyun Liang.,Jiezhang Cao.,Yulun Zhang.,...&Luc Van Gool.(2023).Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis.Machine Intelligence Research,20(6),822-836. |
MLA | Kai Zhang,et al."Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis".Machine Intelligence Research 20.6(2023):822-836. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
MIR-2022-11-351.pdf(7952KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论