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

doi:10.1007/s11633-023-1466-0

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > International Journal of Automation and Computing

	Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
	Kai Zhang 3
刊名	Machine Intelligence Research
	2023
卷号	20 期号:6 页码:822-836
关键词	Blind image denoising, real image denosing data synthesis, Transformer, image signal processing (ISP) pipeline
ISSN号	2731-538X
DOI	10.1007/s11633-023-1466-0
英文摘要	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.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54169]
专题	自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位	1.KU Leuven, Leuven 3000, Belgium 2.Computer Vision Lab, University of Würzburg, Würzburg 97074, Germany 3.Computer Vision Lab, ETH Zürich, Zürich 8092, Switzerland
推荐引用方式 GB/T 7714	Kai Zhang. Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis[J]. Machine Intelligence Research,2023,20(6):822-836.
APA	Kai Zhang.(2023).Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis.Machine Intelligence Research,20(6),822-836.
MLA	Kai Zhang."Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis".Machine Intelligence Research 20.6(2023):822-836.